Awesome AI Dev Tools

A curated collection of AI coding agents, editors, agent orchestrators, sandboxes, and developer tools to supercharge your workflow

Table of Contents

• About
• AI Coding Tools
• Agent Orchestrators
• Agent Sandboxes
• Agent Memory
• More AI Development Tools
• Contributing
• License

About

This repository merges several formerly separate lists into one. Entries are alphabetical within each section.

• AI Coding Tools: Coding agents, CLIs, AI-enhanced editors and IDEs, and code assistants
• Agent Orchestrators: Tools for running, coordinating, and supervising multiple AI coding agents
• Agent Sandboxes: Sandboxes, runtimes, and isolation technologies for running agents and AI-generated code safely
• Agent Memory: Memory layers, MCP memory servers, and benchmarks for giving agents persistent memory
• More AI Development Tools: Personal assistants, agent extensions, app builders, code review and testing tools, and other utilities

AI Coding Tools

Note: All tools are organized alphabetically for easy navigation. Each entry includes a brief description and key features.

16x Prompt - An AI assistant designed to help developers throughout the software development lifecycle.

Aider - An open-source AI pair programming tool that works directly in your terminal, offering Git integration, multi-file editing, and natural language commands for code generation, debugging, refactoring, and automated commits.

aiXcoder - An intelligent programming assistant available as local or cloud-based service, offering predictive coding and extensions for various IDEs.

Amazon Q Developer - AWS's AI coding companion for real-time code suggestions, security scanning, enterprise features, and strong integration with AWS services, available as an IDE plugin and CLI tool.

Amp - An advanced AI coding agent by Sourcegraph available as a VS Code extension and command-line tool, offering multiplayer functionality and cloud-synchronized threads.

Android Studio Bot - An AI assistant tightly integrated into Android Studio, designed to help Android developers generate code, find resources, and learn best practices.

AskCodi - An AI coding assistant with extensions for VS Code, JetBrains, and Sublime Text, offering code generation, explanation, documentation, and test creation features.

Atomic Agent - A local-first CLI and TUI coding agent that runs open-weight models on your machine via llama.cpp, with no account or API key required, built-in tools, MCP support, and local memory.

Augment Code - An AI-powered developer platform for professional engineers and large codebases, with Auggie CLI for terminal-based coding, semantic codebase understanding, resumable sessions, sub-agents, and CI/CD integration.

AutoCodeRover - A project-structure-aware autonomous software engineer that resolves GitHub issues, reporting 46.2% pass@1 on SWE-bench Verified.

Autohand AI - An adaptive continuous engineering platform for automating software development workflows with AI agents.

Baidu Comate - Baidu's AI coding assistant built on its ERNIE models, offering code generation, unit test and comment generation, and codebase Q&A across 100+ programming languages.

Bito AI - An AI assistant that integrates with IDEs and browsers to speed up development tasks, offering code generation, explanation, performance checks, security analysis, and more.

Blackbox AI - An AI coding assistant available as a VS Code extension and web interface, offering autocomplete, chat, and links to online coding references.

Bloop - An AI-powered tool for natural language search across repositories and codebase understanding.

Buildt - A tool for natural language search across repositories (currently waitlisted).

cecli - A community fork of Aider (formerly aider-ce) that keeps the git-integrated pair-programming CLI in active development, adding extensibility and customization hooks.

ChatIDE - A VSCode extension that allows you to chat with ChatGPT directly within the editor.

Claude Code - Anthropic's official agentic CLI coding tool that runs in your terminal, understands your codebase, and executes multi-step tasks through natural language. Supports VS Code and JetBrains IDE integration, GitHub/GitLab workflows, MCP servers, and multi-agent orchestration.

Cline - A VS Code extension and open-source AI coding assistant, with Cline CLI for terminal-based interactive and headless workflows that can execute commands, manage files, interact with browsers, automate CI/CD, and support multiple AI models.

Codebuff - A terminal-based coding assistant that uses natural language to modify codebases across 11 languages.

CodeComplete - A self-hosted enterprise code completion assistant.

Codeep - An open-source terminal AI coding agent that autonomously reads, edits, and verifies code across major providers including DeepSeek, Claude, and Gemini, with self-healing test runs and a VS Code extension.

CodeGeeX - An open-source AI assistant based on the CodeGeeX LLM, offering chat, completion, and refactoring features across multiple editors.

Codegen - A GPT-4 based PR agent designed for enterprise codebases.

CodeMate - A VS Code extension designed for debugging and optimizing code with AI assistance.

CodeStory - An IDE (forked from VSCodium) with integrated chat, code explanations, auto-generated commits, and PR summaries.

Codewhale - Open-source terminal coding agent written in Rust that works with any provider or model.

CodeWP - AI tools specifically trained for WordPress developers, offering code generation for snippets and plugins.

Command Code - A CLI-based AI coding agent that learns a developer's coding style, supports multiple LLM providers, and can build features, fix bugs, write tests, refactor code, and generate commits or pull requests.

Cosine - Trains AI models and specialized coding agents for organizations that need frontier capability within secure environments.

CoStrict - Open-source (Apache-2.0) enterprise-focused AI coder with an agent, code review, and code completion, built around quality-first output.

Crush - A terminal-based AI coding assistant by Charmbracelet that brings agentic AI capabilities directly to your command line, supporting multiple LLMs, LSP integration, Model Context Protocol (MCP) servers, and cross-platform compatibility.

CruxCLI - A provider-agnostic open-source terminal AI coding agent with 24 task-specific modes that automatically map to model tiers, per-mode token budgets, workspace checkpoints, and support for 75+ LLM providers including Anthropic, OpenAI, Google, and Ollama.

Cursor - An AI-first code editor and CLI built on a VS Code fork, deeply integrating AI features like codebase-aware chat, terminal agents, code generation, debugging assistance, and automated code migration.

Deep Agents CLI - LangChain's open-source terminal coding agent built on the Deep Agents SDK, with file editing, shell execution, task planning, persistent memory, sub-agents, MCP tools, and human-in-the-loop approvals.

DeepSeek Harness - DeepSeek's open-source, MIT-licensed terminal coding agent (dsh) where everything is a plugin.

Devin - An AI software engineer developed by Cognition Labs, capable of autonomously handling entire software development projects from planning to deployment.

DevOpsGPT - An AI-Driven Software Development Automation Solution.

Duckie - A web-based chat assistant designed for modifying GitHub repositories.

EasyCode - A VS Code extension featuring GPT-4 powered chat for coding assistance.

Editor.do - A leading AI-powered code editor.

Empryo - A coding harness for terminal, desktop, and CI that maps the repository before editing, edits by symbol through AST and LSP, then runs typecheck, lint, and tests. Works with many providers or existing ChatGPT, Copilot, and Gemini plans. Source-available (BUSL-1.1), not OSI open source.

Every Code - A fork of the Codex CLI with validation, browser integration, and multi-agent orchestration across OpenAI, Claude, Gemini, and other providers.

Factory - An AI-powered platform for code generation agents, including Droid CLI for terminal-based development workflows, codebase understanding, automation, and CI/CD integration.

FauxPilot - An open-source code completion server compatible with CodeGen.

Fine - An AI Dev Environment for automating mundane work, integrating with GitHub, Sentry, and Linear for context-aware answers and automated CI/CD.

Firebender - An AI coding agent built for Android Studio and IntelliJ, focused on Kotlin and Android development.

ForgeCode - A CLI-based AI coding harness with multi-agent workflows, flexible model selection, custom agents, and codebase context tools for terminal-driven development.

Fynix - An AI coding assistant designed to help developers throughout the SDLC.

Gemini CLI - Google's open-source CLI coding agent with a 1M token context window, a generous free tier of 1,000 requests per day with a personal Google account, MCP support, and access to Gemini 2.5 Pro.

Genie AI - ChatGPT - VS Code - A VS Code extension that integrates ChatGPT for coding assistance.

GitHub Copilot - Microsoft's flagship AI coding assistant powered by OpenAI, providing real-time code suggestions, chat, and pull request generation across popular IDEs.

GitHub Copilot Agent Mode - An advanced feature of GitHub Copilot that enables autonomous execution of complex coding tasks, including error detection and self-healing.

GitHub Copilot CLI - Uses AI to translate natural language commands into shell commands.

GitHub Copilot Workspace - An AI-enhanced development environment that streamlines the software development process by generating development plans and enabling integrated code execution from GitHub issues.

GitLab Code Suggestions - AI-powered code suggestions integrated into GitLab.

GitLab Duo - GitLab's suite of AI capabilities integrated across the software development lifecycle, including code suggestions, issue summarization, and vulnerability explanation.

Google Antigravity - Google's agent-first IDE where coding agents plan, execute, and verify tasks across the editor, terminal, and browser.

Google Cloud Code AI (Duet AI) - Google's AI-powered collaborator integrated into Google Cloud services and IDEs, providing code assistance, chat support for Google Cloud queries, and smart actions.

Google Gemini Code Assist - Google's AI-powered code assistance, integrated into its development tools.

Goose - An open-source, extensible AI agent by Block/AAIF that runs locally as a CLI or desktop app, automating coding tasks with support for 100+ LLM providers and MCP extensions for GitHub, databases, and other services.

GPT Engineer - An open-source CLI agent that aims to generate entire codebases from a high-level prompt, asking clarifying questions as needed.

gptme - An open-source terminal agent that writes code, edits files, runs shell commands, and browses the web, with support for building persistent autonomous agents with git-backed memory.

Greptile - A tool for natural language search across repositories and an AI code review bot for GitHub/GitLab.

Grit - A GitHub-integrated agent for automating maintenance tasks and other development work.

Grok Build - xAI's open-source (Apache-2.0) coding agent harness and fullscreen terminal UI with plan mode, subagents, and MCP support.

Groq Code CLI - An open-source, lightweight TypeScript CLI blueprint for building AI-powered coding agents with Groq's fast inference, slash commands, session memory, and customizable system prompts.

Gru.ai - An AI developer that can help solve technical problems and tackle daily coding tasks, such as building algorithms, debugging, and testing solutions.

IBM Bob - IBM's agentic development partner for IDE and terminal workflows, supporting code generation, modernization, security scanning, subagents, and CI/CD automation.

IBM watsonx Code Assistant for Z - An AI-powered mainframe application modernization product with code generation, discovery, and automated refactoring (COBOL to Java conversion).

Imagera Code - A terminal AI coding agent built on OpenCode that edits your project and runs commands and tests, with Claude, GPT, Gemini and many other models on one subscription (paid).

Incognito Pilot - An open-source AI assistant with a built-in Python editor and interpreter.

jcode - A high-performance coding agent harness written in Rust, built for heavy multi-agent development workflows.

JetBrains AI - Built-in AI features across all JetBrains IDEs, offering code completion, chat, documentation generation, and commit message suggestions.

Jules - Google's asynchronous AI coding assistant that operates on GitHub repositories, cloning projects into secure VMs to execute tasks like building features, fixing bugs, and writing tests, with changes presented as pull requests for review.

Junie - JetBrains' AI coding agent for Python, Kotlin, and Java, featuring adaptive learning and deep IDE integration.

Kilo Code - An open-source AI coding assistant for planning, building, and fixing code inside VS Code.

Kimi Code CLI - Kimi's terminal-based AI coding agent for reading and editing code, running commands, understanding large projects, and automating software development tasks.

Kiro.dev - An AI-powered IDE by Amazon built on a VS Code fork, focused on spec-driven development and agentic workflows for cloud projects, featuring autonomous agent hooks, AWS resource scaffolding, and multimodal chat.

Kode CLI - An open-source terminal coding agent that handles software and computer tasks with a single unit agent.

Kodezi - A comprehensive AI-powered developer tool for code assistance.

Kodu - A privacy-focused VS Code extension that operates locally and supports multiple languages for AI coding assistance.

Letta Code - A memory-first AI coding agent with persistent agents that learn across sessions, portable memory across models, skills, and CLI, desktop, and chat integrations.

Magnet - A web-based chatbot that provides context from repositories and issues for coding assistance.

MarsCode - A cloud-based IDE with an AI assistant supporting over 100 languages and intelligent code completion.

Mastra Code - A terminal-based AI coding agent built on Mastra's agent and memory primitives, supporting thousands of AI models with Build, Plan, and Fast modes, MCP servers, and project-scoped thread persistence.

Melty - An open-source VS Code fork with built-in chat, change previews, and the ability to write AI-powered commit messages.

Mentat - A CLI assistant and agent that makes changes to repositories based on AI understanding.

Micro Agent by Builder - An AI agent that writes and fixes code based on provided context and instructions.

MiMo Code - Xiaomi MiMo's long-horizon coding agent initiative, focused on computation, memory, and evolution for coding workflows.

MiniMax Code - MiniMax's open-source terminal coding agent, powered by MiniMax models.

Mistral Vibe - Mistral AI's terminal-native coding agent powered by Devstral models, with multi-file context, autonomous command execution, IDE integration, offline support, and custom subagents.

Nanocoder - A local-first, open-source terminal coding agent with interactive and non-interactive modes, multi-provider support, local model support, and community-driven development.

Oh My Pi - A terminal coding agent with the IDE wired in, built by Stencil Labs. Open source (MIT).

Ona - Runs background coding agents in the cloud as a team of AI software engineers, with orchestration, governance, and kernel-level isolation.

Onuro AI - A leading AI-powered code editor.

OpenAI Codex - The underlying model powering many AI coding tools, designed for code generation and understanding.

OpenAI Codex CLI - OpenAI's open-source terminal coding agent (built in Rust) that reads, edits, and runs code locally with sandboxed execution, full-auto mode, MCP support, and sub-agent orchestration. Usable via ChatGPT Plus/Pro subscription or API key.

OpenBlock OB-1 - A self-improving AI coding agent from OpenBlock Labs for terminal and workflow automation, with multi-model support, reusable skills, session forking, and integrations with GitHub, Linear, Slack, and VS Code.

openclaude - A terminal coding agent that runs anywhere and works with any model provider.

OpenCode - An open-source AI coding agent built for the terminal, desktop, and IDE workflows, with multi-provider model support, LSP integration, session management, and code-editing tools.

OpenHands - An open-source AI development assistant with multi-language support.

Open Interpreter - An open-source coding agent for open models.

OpenSquilla - A self-hostable agent runtime with a CLI (chat REPL and one-shot mode) that edits files, runs shell commands, and uses git tools. Includes tier-based model routing, sandboxing, persistent memory, and 20+ providers.

PearAI - An open-source fork of VS Code with integrated chat and inline code generation capabilities.

Pi Agent IDE - An agent-native IDE extension for Pi with guarded editing, AST/LSP navigation, persistent terminals, debugging, visual inspection, diagnostics, undo, and progressive capability guides through one unified tool interface.

Pi Coding Agent - A minimal, extensible terminal coding agent with multi-provider model support, tree-structured sessions, TypeScript extensions, skills, prompt templates, and scripting or SDK modes.

Pieces - An AI-enabled desktop application and browser extension for code capture, enrichment, and reuse, with on-device processing and multi-IDE integration.

Plandex - An open-source, terminal-based AI coding engine designed for complex projects, allowing for multi-step planning and execution.

Poolside - A company focused on building advanced code generation models.

PoorCoder - A collection of Bash scripts that assist coding using AI apps like Claude and ChatGPT, by extracting code context and generating AI commit messages.

Prime Agent - A self-improving terminal coding agent from Prime Intellect where a persistent IPython kernel is the model's only tool, so file edits, shell commands, and subagents all run as Python. Keeps memories, skills, and subagent specs as durable state, with daemon-backed sessions that survive terminal disconnects.

Project IDX - Google's cloud-based IDE with Gemini AI integration, built on VS Code core, offering multi-framework and multiplatform support.

PromptMate - A VSCode extension that embeds ChatGPT for coding assistance.

PyCharm - A popular IDE for Python development that includes intelligent code assistance features, now enhanced with JetBrains AI.

Pydantic Deep Agents - A terminal coding agent built on Pydantic AI that edits files, runs shell commands, plans, delegates to sub-agents, and connects to MCP servers. Works with any model, including local ones through Ollama, with optional Docker-sandboxed execution; also available as a Python library.

Pythagora - A VS Code extension for natural language app development, featuring a multi-agent architecture and autonomous deployment capabilities.

Qoder - An agentic coding platform with Quest Mode for autonomous task execution, available as an AI-native IDE, JetBrains plugin, and CLI, featuring deep codebase analysis, automated documentation (RepoWiki), and Model Context Protocol (MCP) support.

Qodo AI - A quality-focused generative AI coding platform (formerly Codium) with specialized agents for code generation, test coverage, and merge assistance.

Qwen Code - An open-source terminal AI coding agent optimized for Qwen models, with multi-provider support, built-in tools, skills, sub-agents, and IDE integrations.

Reasonix - A Go coding agent distributed as a single binary, built for long unattended runs. Use it from the terminal, a desktop app, a browser, or an editor over ACP, with configurable providers, plan mode, MCP, a workspace sandbox, and per-turn checkpoints.

Replit - A cloud-based IDE with AI-powered coding assistance (Ghostwriter), real-time collaboration, and instant deployment features.

Replit Agent - Replit's multi-agent system for building applications through natural language, featuring automated environment setup and deployment.

Replit Ghostwriter - Replit's integrated AI coding assistant, offering code completion, generation, transformation, and explanation within the online IDE.

Roomote - Cloud coding agent from the Roo Code team that runs tasks end to end from Slack, GitHub, and Linear and returns pull requests. Source-available and self-hostable.

Rovo Dev CLI - Atlassian's terminal-based AI coding agent for code generation, review, refactoring, debugging, documentation, unit tests, Jira work items, Confluence content, and MCP-powered workflows.

Rubberduck - An open-source chat assistant for the Visual Studio Code sidebar.

Smol Developer - A CLI agent that generates entire repositories from a prompt, using OpenAI and Anthropic.

Sourcegraph Cody - An AI assistant with deep codebase understanding, offering chat, refactoring, and code generation with enterprise features.

StackSpot AI - An AI code assistant.

Supermaven - A VS Code extension offering AI-powered autocomplete with a large 300,000-token context window.

SWE-agent - A CLI agent from Princeton NLP that autonomously fixes GitHub issues and coding challenges using any LLM, featuring a specialized agent-computer interface and support for SWE-bench benchmarking.

Sweep - An AI-powered coding assistant and GitHub integration that generates, tests, and self-reviews pull requests from issues.

SwePT - An open-source pull request generator written in Python.

Tabby - An open-source, self-hosted code completion assistant.

Tabnine - An AI code completion assistant that emphasizes privacy, offering local models and custom training on your codebase.

talk-codebase - A CLI chatbot that uses repository context with OpenAI or local LLMs.

Theia IDE - An extensible open-source IDE (web and desktop) with Theia Coder, an AI-powered coding agent that can browse workspaces, propose code changes, and automatically detect and fix issues, with Edit Mode and Agent Mode options.

Tianshu Harness - A TypeScript coding-agent runtime with one kernel for a terminal TUI and a desktop GUI. It tracks goals, evidence, and completion so a model's claim of "done" is not taken at face value, and supports multi-agent orchestration.

Tongyi Lingma - Alibaba Cloud's AI coding assistant with inline code completion, multi-file editing, and an agent mode that plans tasks and uses search and terminal tools. Available as a plugin for VS Code, Visual Studio, and JetBrains IDEs, and as the standalone Lingma IDE; free for individuals.

Trae - ByteDance's AI-powered IDE with GPT-4 and Claude integration, featuring Builder and Chat modes.

Twinny - An Ollama-based AI code completion plugin.

Unblocked - An AI-powered code context and chat assistant with integration across GitHub, Slack, and Jira.

Verdent - An agentic coding suite with parallel agents, plan mode, and bring-your-own-key support for VS Code, JetBrains, Mac, and Windows.

Void - An open-source AI-powered code editor with local model hosting support.

Vorflux - Cloud agents that run the full software development lifecycle on dedicated machines and ship production code.

VT Code - An open-source Rust terminal coding agent with multi-provider LLM support, automatic failover, context management, and shell safety controls.

Warp - A modern terminal emulator with AI command assistance, block-based organization, and team collaboration features.

Wave Terminal - An open-source terminal with built-in AI chat, inline file previews, a web browser, and persistent remote sessions.

Windsurf AI - An advanced IDE by Codeium with Cascade technology for deep context awareness, multi-file editing, real-time collaboration, and VS Code compatibility.

ZCode - Z.ai's AI coding environment for planning, coding, reviewing, and deploying with GLM-optimized agentic workflows and multi-agent collaboration.

Zed - A high-performance, multiplayer code editor with Claude 3.5 Sonnet integration and real-time streaming diffs.

Zencoder - An advanced AI platform featuring Repo Grokking™ technology for deep codebase understanding and an Agentic Pipeline with self-improving AI agents.

Zero - A terminal-based AI coding agent focused on user-owned workflows for reading, editing, and managing code from the command line.

ZZZ Code AI - An AI code assistant.

Agent Orchestrators

Note: All tools are organized alphabetically for easy navigation. Each entry includes a brief description and key features. Entries ending in a last commit note have had no recent activity.

1code - Orchestration layer for Claude Code and Codex. (last commit 2026-03; archived)

5dive - Named agents on a shared org chart and backlog hand work to each other and escalate to a human over Telegram. Claude Code, Codex, Grok, Antigravity, OpenCode.

aeon - Runs unattended on GitHub Actions; dispatches skills to six coding-agent harnesses behind one contract (Claude Code, Grok, Codex, Pi, Vibe, Kimi), with quality scoring, git-persisted memory, a self-healing loop, and reactive triggers.

Agent Barn - Open-source (Apache-2.0) control plane for AI agents: teams talk to agents in Slack, Teams, Telegram, Discord or email, agents work across Jira, GitHub, Confluence and more, and every conversation, tool call, log and cost is recorded. Runs agent runtimes like Hermes and OpenClaw on your own Kubernetes cluster, deployed with Helm.

Agent Console - Terminal-first Tauri desktop app that runs the real agent CLIs in PTYs with per-turn snapshots, diff review, and rewind, and witnesses every prompt, approval, and tool result into a hash-chained ledger exportable as a signed proof packet or an IETF audit trail anyone verifies offline; multi-engine rooms, push-to-talk voice with local TTS, and an MCP server so agents can drive the console. Linux, macOS, Windows. Claude Code, Codex.

Agent Messaging Protocol - Open standard for agent-to-agent messaging with Ed25519-signed envelopes, federation across providers, and delivery that must be proven rather than assumed. Reference server, TypeScript SDK, and a Claude Code plugin.

Agent Teams - Desktop app where you give high-level commands to autonomous coding-agent teams across Claude Code, Codex, OpenCode, Cursor, Grok, GitHub Copilot, Kiro, Z.AI, MiniMax, Kimi, 200+ models, and 75+ LLM providers. Agents coordinate through inter-agent messaging, Kanban tasks, and built-in code review.

agent-console - Rust TUI that finds Codex and Claude Code sessions from the providers' own transcripts, including ones started elsewhere, and resumes their native UI rather than replacing it. No tmux or worktrees.

agent-deck - One TUI covering sessions across Claude Code, Codex, Gemini, and OpenCode, with live status and resume for each.

agent-kanban - Leader-worker task board with cryptographic agent identity. Claude Code, Codex, Gemini CLI.

agent-manager - Live-status tmux TUI with a prompt that lands in the pane without attaching, and in-terminal diff review that sends line comments back to the agent. Claude Code, Codex, OpenCode, Grok, Gemini CLI, Pi, Hermes.

agent-of-empires - Pairs a TUI with a matching web view, so the same sessions stay reachable from a phone. Claude Code, Codex, OpenCode, Gemini, Mistral Vibe.

agent-qa - Runs natural-language web and mobile test suites through a self-healing execution loop, persists memory between runs, and exposes a dashboard, CLI, MCP server, and coding-agent skills.

agent-runbook - Compiles YAML runbooks with loops, branching, and parallelism into SKILL.md files for Claude Code and Codex.

agent-session-manager - Live tmux TUI with session groups, resume and fork, diff review, and mobile push when an agent needs an answer. Claude Code, Codex, Gemini, Aider, Amazon Q, OpenCode.

agent-session-manager-desktop - Desktop GUI over tmux where each session holds agent and shell tabs with per-tab working directories; waiting agents raise a header counter you can answer without switching tabs, and ntfy push carries it to your phone. Linux, macOS, Windows. Claude Code, Codex, Gemini, Aider.

agent-squid - Browser UI organized into named lanes (#topic@agent), with context shared across agents and a realtime quota gauge.

agent-swarm - Self-hosted AI company operating system where a lead agent delegates goals to workers in isolated containers, with persistent memory, schedules, and review gates. Claude Code, Codex, pi, OpenCode, Cursor, Amp, Grok, Devin, and ACP agents.

agentbox - Gives each agent its own sandboxed VM — local Docker or cloud via Hetzner, Daytona, Vercel, or E2B — with sub-second checkpoint starts.

AgentBridge - Local MIT CLI that keeps Claude Code and Codex as live peers in one session for mid-turn review, task split, and quota-boundary handoff.

agentglass - Desktop workspace for a fleet of coding agents: terminals that survive reboot, a built-in browser agents drive, live cost per session, a hold on risky actions, PR and task boards, and a phone companion. Claude Code, Codex, OpenCode, Gemini CLI.

Agentlas OS - Keeps specialist agents in a hub and spins up a temporary orchestrator per task, with A2A routing and governed memory gates. Formerly Hephaestus.

agentsmesh - Remote AI workstations with PTY sandboxes and worktree isolation, coordinating across channels and pod bindings. Claude Code, Codex, Gemini CLI, Aider, OpenCode.

agenttier - Kubernetes runtime giving each agent its own Pod and PVC sandbox behind a default-deny NetworkPolicy, with a streaming SSE invoke API.

aGiTrack - Takes what a coding agent produces and commits each turn to git, recording the prompt, model, and that turn's token cost in the commit message, with the agent confined to its own worktree. Claude Code, Codex, and OpenCode.

Agon - Orchestrates scientist, coder, and auditor loops from research topic through proposal to experiment.

Agora - Self-hosted chat where coding agents on different machines coordinate in shared channels and threads, with turn-taking, file reservations, and handoffs, while humans watch and steer from a web UI. Claude Code, Codex, and any MCP client.

agterm - Native macOS terminal with named workspaces, a live dashboard, attention states, and a scriptable control API.

AGX - Wake-work-sleep checkpointing keeps a persistent agent team on long objectives, with human gates between cycles.

ai-devkit - CLI control plane that runs agent sessions in managed tmux, sends prompts and logs to running agents from the terminal or a TUI console, and gives every agent one setup with shared local memory, verification skills, and lifecycle workflows. Claude Code, Codex, Pi, and more.

ai-maestro - Dashboard spanning multiple machines, adding memory search, code-graph queries, and agent-to-agent messaging. Claude, Aider, Cursor.

AI4Kanban - AI project manager that turns rough ideas into actionable tasks, coordinates coding agents through planning and implementation, and builds shared project memory from decisions. Humans steer priorities and make key decisions through a desktop and web interface.

AIWG - Deploys versioned agents, skills, rules, and governed workflows into the native project paths used by Claude Code, Codex, Copilot, Cursor, and other coding agents.

AIWorks - MIT-licensed supervisor for one Windows PC that runs Claude Code, Codex, and Cursor through an approved plan in isolated git worktrees, has a separate session verify each step, and delivers pull requests to GitHub; it keeps going through crashes, restarts, and usage limits and asks the owner only for decisions. Early preview; real worker execution is Windows-only, and the synthetic-data dashboard demo also runs on Linux and macOS.

aizen - macOS workspace that organizes worktrees, environments, and agent sessions per project.

alas - Native macOS workspace for the whole agent loop: libghostty terminals or native chat panes across every worktree, on your Mac or over SSH, with comment-based review, in-app merge, and pickup from your phone.

Alchemist Coder - Desktop app that shows each agent and every subagent it spawns as a live tree, runs up to four agents on one approved plan in separate Git worktrees, and has a coordinator agent that hands work to agents you configure. Runs Claude Code and Codex over ACP on local models (Ollama, LM Studio); macOS, Windows, Linux.

Alethe - Local-first desktop workspace where agents and shells run as real PTYs in split panes and custom grids across projects, surviving pane close and app restart. Suspend idle groups to reclaim memory and resume with scrollback intact. Claude Code, Codex, OpenCode.

Alook - Shared rooms where people and agents collaborate: local coding agents get persistent identities with handles, inboxes, and memberships, while agents keep running on your own machine.

amux - Minimal TUI for spawning parallel coding agents in git worktrees.

antfarm - Build your agent team in OpenClaw with one command. (last commit 2026-02)

Aperant - Runs up to 12 agent terminals with a self-validating QA loop and automatic conflict resolution when merging back to main.

Archon - Harness builder for deterministic AI coding workflows, combining agent steps with scripts, validation gates, approvals, and isolated git worktrees. Claude Code, Codex, and more.

assistant - Panel-based assistant whose plugins share one workspace of notes, lists, and objects.

ateam - macOS and iPhone app orchestrating Claude Code, OpenCode, and Codex crews, each isolated in its own git worktree.

automaker - Describe features on a Kanban board and agents implement them in isolated worktrees, running tests and committing as they go.

automata - Matrix-native workspace where Temporal-backed durable workflows survive restarts and keep long tasks moving.

AX - Google's declarative runtime for running autonomous agent workloads at cluster scale: Kubernetes-style task specs, sandboxed workspaces, and network fencing.

babyagi3 - A minimal AI agent you configure once, then run through natural language. (last commit 2026-03)

background-agents - Sessions trigger from a web UI, Slack, GitHub, Linear, webhooks, or cron, run in Modal, Daytona, Vercel, E2B, or OpenComputer sandboxes, and open attributed PRs.

bb - Self-controlling agentic IDE that orchestrates multiple coding agents in live threads you can follow, steer, or hand off, driven from a desktop app, web app, CLI, or HTTP API.

Berd - Block's open-source desktop app for working with AI agents: project chats with per-folder worktree behavior over the Goose backend, with agents, skills, connections, and agent sharing in one place.

bernstein - Keeps no model in the coordination loop, so orchestration costs zero tokens. Verifies with tests and auto-commits across 40+ CLI agents.

BMAD Method - Agile framework of specialized agent personas (analyst, architect, developer, QA) for planning and building with coding agents.

Borg - Security-first assistant in Rust built to run unattended, with a sandbox on by default, self-healing, long-term memory, schedules, and sub-agents, reachable over Telegram, Slack, Discord, Signal, WhatsApp, iMessage, a TUI, or a desktop app.

Boxes.dev - Gives every Claude Code or Codex agent its own cloud computer on your existing subscription, with agents started from Slack or Linear and managed from desktop, phone, or terminal.

Brow - GPL-3.0 macOS app for running parallel Claude Code sessions on a multi-repo project: its menu-bar Workspaces gives each feature one folder holding a git worktree of every chosen repository, all on one branch, and moves a session to another Claude account, while the MacBook notch shows every account's 5-hour and weekly limits. Requires macOS 26+ on Apple silicon.

buzz - Agents are first-class members of shared channels on a Nostr relay you own, with their own keys and audit trails. Claude Code, Codex, Goose.

Calyx - Native macOS terminal built on libghostty with an approval inbox for permission prompts, a working/blocked/idle sidebar, and in-terminal diff review.

cashclaw - An autonomous agent that takes work, does work, gets paid, and gets better at it. (last commit 2026-03)

ccswarm - MIT-licensed Rust Sangha workflow engine for Claude Code and Codex planning, quorum assessment, parallel implementation, review, and fixes. Approval markers do not prove required checks; Codex readonly review currently uses workspace-write, replay re-executes, and undo only reports commits.

centaur - Multiplayer self-hosted agents with Slack-native conversations, Kubernetes sandboxes, shared tools, and durable workflows.

Cezar - Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi, and other coding agents in parallel — locally or 24/7 on your own server.

Claude Command Center (CCC) - Local dashboard for spawning, monitoring, and resuming sessions across Claude Code, Codex, Cursor, Antigravity, and Kilo Code.

claude-code-action - Anthropic's official GitHub Action, detecting from context whether to answer, review, or implement. Auth via Anthropic API, Bedrock, Vertex, or Foundry.

claude-squad - Runs each agent as a detached background session with its own worktree, so work continues after you close the pane. Claude Code, Codex, OpenCode, Amp.

claude_code_bridge - Real-time multi-AI collaboration.

claude_codex_bridge - Workspace for mixing different vendors' CLI agents in one visible collaboration session.

Claudexor - Routes one coding thread across harnesses with quota-aware rotation between subscription profiles, Best-of-N runs, and cross-family review.

clave - Native macOS app with split and grid layouts, session groups, SSH remote sessions, and usage analytics for Claude Code.

clawe - Multi-agent coordination system: think Trello for OpenClaw agents. (last commit 2026-02)

ClawTeam - Agents spawn and manage their own teammates from one command, coordinating through file-based or P2P inboxes across tmux worktrees.

CLI Agent Orchestrator (CAO) - Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions.

clideck - Chat-app-style dashboard with autopilot routing between agents and full control from a phone. Claude Code, Codex, Gemini CLI, OpenCode.

Cloudflare OS - Self-hostable "company OS" on Cloudflare Workers: a chat UI where agents preloaded with your company context do tasks, build sandboxed apps, and stay inside a Gatekeepers guardrail framework.

Cloudroom - Desktop app for AI coding agents on your Mac or in the cloud: each thread gets its own sandbox and Git branch, running threads teleport between local and cloud, and the core is self-hostable.

cmux - Ghostty-based macOS terminal with vertical tabs and per-agent notifications, built for keeping many concurrent sessions legible.

Codealong - Open-source desktop app for macOS and Linux that tracks every Claude Code, Codex, OpenCode, Antigravity and Cursor session on your machine, grouped by repo, worktree and PR, with a floating bar for approvals and replies and plan usage per account.

codecast - Watches your real local sessions and surfaces them in a live triage inbox, keeping a searchable record with line-level agent attribution. Claude Code, Codex, Cursor, Gemini.

CodeNomad - Desktop and web workspace around the OpenCode CLI whose SideCars embed local tools like VS Code and terminals as tabs.

codex-action - OpenAI's official GitHub Action, running Codex CLI headlessly under drop-sudo, unprivileged-user, or fully read-only sandboxes.

CodexMonitor - Orchestrate multiple Codex agents across local workspaces. (last commit 2026-03)

Coincide - Open-source (MIT) native macOS app that drives the official CLIs of Claude Code, Codex, Cursor, Grok Build, OpenCode and Antigravity with your existing logins, with one model picker and the ability to switch agents mid-thread.

collaborator - Arranges terminals, editors, and files as tiles on an infinite pan-and-zoom canvas instead of tabs.

Comma - Sessionless personal agent that breaks goals into tasks and keeps working through agentic loops across your computer, phone, and browser, with computer use, files, and remote control; self-hostable (AGPL-3.0).

Commonly - Apache-2.0 pods where a team's people and the agents each person runs (Claude Code or Codex from a Mac, or a hosted agent) share conversations and one task board, claim tasks, and send decision cards to a person.

CompanyHelm - Distributed orchestrator with task management and direct agent-to-agent conversations.

Concord MCP - Shared coordination protocol for Claude Code, Codex, Cursor, Gemini CLI, and Grok Build agents to claim work, detect edit collisions, exchange durable messages, transfer ownership, and hand off review evidence without replacing their existing harnesses.

Conductor - Mac app for running parallel Claude Code and Codex agents in isolated git worktrees.

constellagent - macOS app giving each agent its own terminal, editor, and git worktree in a single window.

Contrabass - Terminal-first orchestrator for issue-driven agent runs, pulling work from Linear, GitHub Issues, or a local board into git worktrees with TUI, headless, and dashboard modes.

corellis - Multi-agent governance framework for OpenClaw — goal decomposition, fleet-wide memory, correction propagation, and approval workflows for 20+ agent fleets.

Cotal - Open pub/sub standard over NATS JetStream where mixed coding agents share a space with presence, channels, durable direct messages, and role-addressed anycast, in any topology you wire. Claude Code, Codex, OpenCode, Hermes, Jcode, and pi.

Coterie - Apache-2.0 self-hosted team of persistent Claude Code agents on one Debian host: each agent has its own Unix account and terminal, boots from a shared MCP memory server (identity, team state and unread mail, with a hashed manifest of what it was sent), and gets maildir mail that rings its terminal when idle; a browser page shows every agent's pane. Installs with one pasted line and a guided setup; needs a Claude Code login per agent, and setup writes a dispatch block into each agent's CLAUDE.md and hooks into its settings.

Coven - MIT-licensed local-first Rust daemon and CLI that runs Codex, Claude Code, and other coding-agent harnesses as PTY sessions inside explicit project-root boundaries, with SQLite-persisted history and a versioned local socket API.

Coworker - Open source AI coworker that lives on your desktop. Formerly accomplish.

Coworkers - AI teammates that each get their own computer and browser, built entirely on Cloudflare: give each bot a job and it works while you're away, asking before anything risky.

crewAI - Framework for orchestrating role-playing, autonomous AI agents that collaborate through defined roles, tools, and task delegation.

Crewly - Runs teams of role-based coding agents with task delegation, shared memory and a live web dashboard. Claude Code, Codex, Gemini CLI, OpenCode.

Crewplane - CLI-first control plane that turns one-off coding-agent calls into reviewable Markdown workflows spanning Claude Code, Codex, Gemini CLI, or Copilot CLI. Explicit artifact handoffs keep execution inspectable on disk, while validated completed nodes let failed workflows resume instead of starting over.

crystal - Run multiple Codex and Claude Code sessions in parallel git worktrees.

Culture - Coordination-oriented system with rooms, protocol docs, agent lifecycle patterns, and multiple clients.

Cyclops - Coordinates coding agents running in tmux through a durable mailbox with guarded terminal notifications, FIFO delivery per recipient, and fail-closed human-composer protection, with an optional workspace UI for overseeing the team. Codex CLI, Claude Code, Antigravity, Cursor Agent.

cyrus - Watches Linear, GitHub, GitLab, and Slack issues assigned to it, spinning up an isolated worktree per issue. Claude Code, Codex, Cursor, Gemini.

deepseek-harness-action - Runs DeepSeek Harness from GitHub PRs, issues, and CI failures for code reviews, diagnostics, and validated fixes with explicit write controls.

Delegatus - Local web board run by an orchestrator agent you message: it turns requests into tasks, runs each through build and fresh read-only review stages in its own git worktree until a pull request is ready, and brings decisions to you in the browser, on your phone or in Telegram. Claude Code and Codex, with Copilot for single agents.

denchclaw - Managed OpenClaw framework aimed at CRM, sales automation, and outreach.

Dex - Human-gated planning, multi-reviewer code review, and dead-end-aware research loops, shipped as cross-platform binaries for 7 CLI backends.

diri - Native macOS app running Claude Code, Codex, Cursor, Gemini, and shells in parallel across git worktrees or remote hosts, with live status, session persistence across restarts, a menu-bar rollup, and an MCP server for agents to spawn others.

dmux - Dev agent multiplexer pairing coding agents with git worktrees over tmux.

DockTerm - Cross-platform terminal workspace that runs the real Claude Code in one pane per project, with a live sub-agent view, diff review, Git, and permission prompts that pop out of the Mac notch.

dorothy - Desktop app combining agent orchestration with automations, Kanban management, and MCP servers.

Dray - Native desktop app wrapping Claude Code, Codex, fx, and pi in a chat UI, with one worktree per session plus diff, PR, and issue panels and an embedded browser.

Emdash - Agentic development environment running parallel agents against any model provider.

EvoFlux - Local-first desktop workspace coordinating specialist AI agents across conversations, files, terminal, browser, Git, memory, and verification.

Fletch - Native macOS IDE that seals each agent in its own repo clone under Seatbelt or Docker, serves each a shared symbol and call-graph index over MCP, and gates every step on tests or your approval. Claude Code, Codex, Cursor, OpenCode.

Flue - Sandbox agent framework from the Astro team: give each coding agent its own isolated environment with the tools and access it needs.

foremerge - Coordination protocol above Git: agents declare intent, semantic scope, and operation before writing code, deterministic rules raise findings when plans collide, and acceptance is gated on a verification run it executes itself. One Rust binary over local SQLite, with MCP for Claude Code, Codex, and Cursor.

fractal - Loops that recursively delegate separable subtasks to child agents, bounded by configurable depth, cost, and time limits.

Friday - Cross-platform desktop app where agents split work on a shared task board, message each other, and hand a task to another agent with its progress when one hits its usage limit, each in its own git worktree with diff review. Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, and any ACP agent.

Frink - Desktop app that starts a Flow from a ticket (Linear, Jira, Shortcut, ClickUp), an alert or event (Sentry, PostHog, Vercel, Cloudflare, Supabase, and more), any webhook, or a schedule, then runs it as a graph of agent, shell, condition, and approval steps in its own worktree and parks blocked agents in a Work Queue. Claude Code, Codex.

Fusion - Multi-node orchestrator with a kanban board, plan-review-execute gates, per-task worktrees, and hierarchical missions.

future-os - One agent everywhere (terminal, desktop, mobile, CLI, IM bots) with a built-in loop control plane: durable goals, event-sourced state, and verification gates for 24h+ runs.

Garcon - Self-hosted browser and mobile workspace with diff review, Git/PR workflows, mobile approvals, scheduling, and cross-agent transfers. Seven CLI agents.

gastown - Scales to 20-30 agents with a coordinator, git-backed issue tracking, health watchdogs, and a Bors-style merge queue.

gh-aw - Compiles agentic workflows written in Markdown into GitHub Actions YAML. Read-only by default, with writes only through sanitized safe-outputs. Copilot, Claude, Codex, Gemini.

ghast - Multitask with multiple terminals.

ghostclaw - An AI that lives on your computer and does things for you.

Ghostex - Native macOS workspace (Rust/GPUI) running CLI agents side by side in low-RAM Ghostty terminals, with embedded browser and editor panes, a Kanban board, and iOS/Android session access. Claude Code, Codex, OpenCode.

gnap - Git-native agent protocol coordinating agents through a shared repo as a task board, with no orchestrator process. (last commit 2026-03)

GraphCode - macOS app that wires agent sessions into a graph: each node is a live terminal you can attach to mid-run, each edge a hand-off, message, or spawn that fires while you're away. Claude Code, Codex, Copilot CLI, OpenCode, pi.

Grux - Native macOS agent that runs agent swarms in parallel, opens terminal sessions it can undo, and reaches your mail, calendar and meetings; runs on a local Ollama model or your own Anthropic key, and any coding agent can drive it over MCP or its CLI.

guild - Shared context, memory, and task coordination as a single Go binary over local SQLite with hybrid keyword and semantic search.

handoff - Delegates a task to DeepSeek, Codex, or Claude from inside your current Claude Code or Codex session, returning the result automatically.

Happy - Desktop app and CLI running agent sessions side by side on your own machine or server, with an end-to-end encrypted iOS/Android app for the same sessions. Claude Code, Codex, and Grok in the desktop app; Claude Code, Codex, and any ACP agent from the CLI.

Harness by Autonomous - Open-source desktop and mobile command center for supervising Claude Code, Codex, OpenCode, and other coding agents across machines.

hcom - Lets agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity, Cursor, OpenCode, Kilo, and more.

Helicon - Unofficial desktop and web app, not affiliated with Meta, that puts threads from every project in one sidebar with inline diffs, approvals, cost tracking, and a VS Code and Cursor extension. Muse Code.

Helmor - Apache-2.0 local-first IDE and workbench for orchestrating Claude Code, Codex, and other coding agents across worktrees through planning, running, review, testing, merge, and shipping loops.

herdr - Background runtime that owns your agents' terminals: sessions survive reboot and reattach from any terminal or SSH, panes are marked working/blocked/idle, and agents themselves spawn panes and prompt each other over a CLI and socket API. One Rust binary.

herduck - Terminal app derived from Herdr: keeps its agent panes and adds a Work view that groups the Claude Code, Codex, OpenCode, and Pi sessions behind one piece of work with its goal, blocker, and next step. Early alpha.

hermes-agent - Self-improving harness with persistent cross-session memory and auto-generated skill documents.

Heym - Self-hosted runtime for tool-using LLM agents and OpenCode workflows, with sub-agent orchestration, MCP integration, approval checkpoints, and execution traces.

Hivekeep - Self-hosted team of specialized agents with persistent memory that delegate and build their own tools and mini-apps. Telegram, Slack, Discord, Matrix. Single container, MIT.

Hotline - Self-hosted chat room for a team of agents you reach from desktop or phone, each with its own Linux computer in a container, plus scheduled jobs, voice calls, and teammates that hand work to each other. Any model; Claude Code and Codex over ACP.

humanlayer - Human-in-the-loop control for coding agents on hard problems; the repo notes its code is now largely deprecated in favor of a rebuild.

Ignite - Desktop app built on pi that runs each conversation in its own git worktree with bash in an OS sandbox, hands tasks off to agents that come back as pull requests, and lets you draw on screenshots to show what's wrong. macOS, Linux, Windows. Claude and ChatGPT subscriptions, plus any provider pi supports.

IM.codes - Mobile and web control layer built for away-from-desk continuation, with terminal access, git views, localhost preview, and scheduled tasks. Claude Code, Codex, Gemini CLI.

Intent - Desktop app for coordinating coding agents at scale: workspaces, notes, tasks, git, and terminals in one place, backed by a Rust daemon, with an iOS companion.

intentic - Browser and mobile workspace where every agent gets a persistent Docker sandbox on a machine you own plus a git worktree of its own, reached over an outbound-only Cloudflare tunnel, so runs keep going after you close the tab. Plan mode, per-hunk diff review, an environment Dockerfile the agent proposes and you approve, credential capabilities injected per turn, and schedule, webhook or event triggers. Claude Code, Codex, Grok, Kimi Code, Gemini. MIT.

ironclaw - Agent OS in Rust focused on privacy, security, and extensibility.

Isomux - Source-available (BSL 1.1, free for organizations of up to 10 people) self-hosted web office for Claude Code, Codex, and OpenCode agents: each agent keeps a name, instructions, and memory across sessions, agents message each other and share rooms and a task board, and several people can talk to the same agents from any device.

iva - Telegram assistant that turns your messages, voice notes and photos into an Obsidian-compatible markdown vault it remembers across sessions. Crons, skills, MCP and Google Workspace from an in-chat menu. Self-hosted in one command, MIT.

ivy-tendril - Drives agents through a plan-based lifecycle with verification gates, self-improving memory, and human checkpoints. Claude Code, Codex, Antigravity, Copilot, OpenCode.

jean - Desktop and web app for orchestrating agents across multiple projects and their git worktrees. Claude, Codex, OpenCode.

jelly - Local-first multi-bot system for running your operation from one VM: persistent agents grouped into project directories, phone-friendly web UI via Tailscale, browser control, and sudo on request.

Joxo - Closed-source, hosted; the public repository holds its Claude Code and Codex plugin. One shared project for the coding agents each teammate runs on their own computer (Claude Code, Codex, Cursor, OpenCode and others): a task board where a task has one holder at a time, decisions every agent reads, and handoffs that carry the branch and commit.

kandev - Kanban workbench whose multi-step workflows assign a different agent per step behind human gates, running locally, in Docker, over SSH, or in cloud executors.

kanzo - Self-hosted kanban for humans and agents: a browser board and an MCP server in one 4 MB binary, so you and your coding agents work on the same tasks and agents move cards while you watch.

kodo - Directs agents through work cycles where a separate agent independently verifies each result. Claude Code, Codex, Gemini CLI.

lalph - Orchestrator driven by whichever source of issues you point it at.

lemon - Local-first assistant and coding agent runtime.

leon - Long-running open-source personal assistant with voice and text interfaces.

lettabot - Personal assistant that remembers everything. (last commit 2026-05; archived, replaced by Letta Code)

LionClaw - Local control plane running coding agents as durable, auditable workers with explicit state, skills, and checkpoints.

lobsterai - Desktop-grade agent for data analysis, slides, docs, and web research.

loki-mode - PRD-to-deployed-product SDLC with 41 agents in 8 swarms, nine quality gates, and blind three-reviewer code review. Source-available under BUSL-1.1.

LongHorizon-Harness - Long-running computer-use harness with fresh-context execution, independent auditing, and verified checkpoints across desktop apps and CLI workflows. Claude Code, Codex, OpenCode, DeepSeek Harness.

Lookout for VS Code - VS Code extension that puts every agent session on one board in the side bar, quotes what a waiting session asks (the command, file or question), jumps to a session's tab or terminal in any VS Code window with one key, and searches every conversation. Reads only what the agents already write on disk, with no hooks, and does not launch agents. Claude Code, Codex, Copilot CLI. MIT.

loom - Infrastructure for evolutionary software where autonomous loops evolve products.

Loop Engineering - Designs repeatable coding-agent loops around automation, worktrees, skills, state, and verification, with starters and a Loop Ready score for Grok, Claude Code, Codex, and OpenCode.

LoopTroop - An LLM council plans the work, then Ralph-style loops retry failed units with fresh context. Executes via OpenCode worktrees.

lorca - E2E-encrypted personal agent chat: create bots, talk 1:1 or in group chats, and let them hand work to each other. Rust CLI, native macOS client, and phone apps.

lucinate - Terminal-native chat client for OpenClaw, Hermes, Ollama, and OpenAI-compatible providers, with cron management and session browsing.

Machinist - Keeps coding agents working on a repository without making a human orchestrate every step from a terminal, pulling tasks from trusted ticket queues into isolated Codex workspaces.

maestro-orchestrate - Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code with specialist subagents, parallel execution, and persistent sessions.

Markus - The all-in-one AI workforce platform for building AI agent teams: role-based agents that coordinate, delegate tasks, and work toward a shared goal with persistent memory.

MartinLoop - Caps spend, enforces policy, verifies output, and rolls back failures, leaving inspectable run receipts.

Mastra - TypeScript framework for building and orchestrating AI agents and workflows, with memory, tools, evals, and MCP support.

megazord - Claude Code framework for multi-agent coordination.

mercury - Personal AI assistant that lives where you chat. (last commit 2026-03; archived)

Mercury CLI - Terminal coding agent that runs parallel sessions and delegates to crewmates in isolated Git worktrees with file leases, using 22 model providers or local models.

MetaClaw - Assistant that learns and evolves from conversation alone.

Mnemoverse - Hosted memory engine over MCP: decisions, preferences, and lessons follow an agent between sessions and tools, and recall re-ranks from reported outcomes rather than similarity alone. Remote endpoint with sign-in, or npx -y @mnemoverse/mcp-memory-server@latest with an API key. Claude Code, Cursor, Gemini CLI, VS Code, Windsurf, ChatGPT. MIT server, free tier.

MonoCode - Tauri desktop UI where tabs are agent sessions, running Claude Code, Codex, Cursor, Grok Build, OpenCode, Pi, omp, and fx on your existing subscriptions. macOS, Linux, and Windows.

MulmoTerminal - Browser grid of live Claude Code / Codex sessions started with one npx command. Each cell is a real PTY with a colour-coded status, tmux-backed persistence, and a git worktree per cell. For Claude Code, needs-you is shown separately from done, read from the CLI's own hooks.

multi-agent-shogun - Shogun to karo to ashigaru hierarchy running up to 10 agents over tmux with no coordination API cost.

multica - Managed agents platform where you assign tasks, track progress, and let agents compound skills between runs.

MultiCC - Self-hosted workspace where one chat task and its git worktree survive switching from Claude Code to Codex, OpenCode, or another agent; parallel tasks run in isolated worktrees and the same host is reachable from desktop, web, and mobile.

muxel - GPU-accelerated native desktop multiplexer (not a TUI) where every pane embeds a real terminal running a coding agent, with first-class git worktrees, live agent status, scheduled runs, and notifications.

nanobot - Ultra-lightweight self-hosted assistant in Python with WebUI, tools, memory, MCP, and multi-agent workflows.

nanoclaw - Lightweight OpenClaw alternative running in containers, connecting to WhatsApp, Telegram, Slack, Discord, and Gmail.

NarraNexus - Open-source AI agent team workspace by NetMind.AI whose agents remember, collaborate, and use tools from day one.

NEEDLE - Runs unattended against a shared bead queue (SQLite, atomic claims), dispatching each bead to a headless CLI — Claude Code, Codex, OpenCode, Aider — with every outcome routed through an explicit state machine; no inter-agent channel, coordination is done at decomposition time.

NemoClaw - Runs Hermes, LangChain Deep Agents, and OpenClaw inside NVIDIA OpenShell with managed inference.

Network-AI - TypeScript/Node multi-agent orchestrator with shared state.

neuralyzer - Lets an agent wipe its own session context and re-run the first message, making Ralph loops easier to engineer.

nimbalyst - Visual workspace pairing parallel worktree sessions with kanban and direct visual editing. Claude Code, Codex, OpenCode.

Niteshift - A cloud for coding agents that gives Claude Code, Codex, OpenCode, Pi, and others a real environment to run and verify work, and returns a pull request with evidence that it works.

no_human - Takes a ticket (Jira, Linear, monday.com, GitHub/GitLab issues) to a reviewed pull request on your own machine: a second model in a fresh session reviews each diff and is told to refute "done", a tamper guard blocks net test reductions before that review, and merging stays human. Claude Code as the coder; Codex and local backends optional. MIT.

nullclaw - Fully autonomous assistant infrastructure written in Zig.

Nuphos - Desktop and web workspace where a team runs Claude Code and Codex via ACP adapters across people and machines, with sessions that outlive any single laptop.

NXTG-Forge Orchestrator - Coordinates Claude Code, Codex, and Gemini CLI on one shared repo through a research-plan-delegate-adversarial-verify-deploy pipeline, with file locking, knowledge capture, and drift detection. Single Rust binary.

octomux - Local dashboard with a kanban fleet view, one unified permission inbox across agents, and in-app diff review.

Octop - Self-hosted multi-user assistant with a built-in expert team operating in parallel, reachable from web, Telegram, Feishu, DingTalk, QQ, and WeCom.

oh-my-codex - Workflow layer for OpenAI Codex CLI: stronger default sessions, reusable skills, native hooks, HUD/status surfaces, project guidance, and team-style execution commands.

Okto Nexus - Elastic-2.0 local-first MCP coordination hub where agents get durable identities, messaging, single-winner handoff claims, and human-in-the-loop approval on risky actions.

omg.dev - Open-source parallel-agent harness: run coding agents on your own computer or a hosted one, controlled from a single web UI with a mobile client. Claude Code, Codex, Grok, Cursor, OpenCode, Copilot, Pi.

omnigent - Meta-harness running Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, or custom YAML agents against swappable sandbox backends, with policy enforcement.

Opcode - An open-source desktop GUI for Claude Code (formerly Claudia) for managing sessions, custom agents, usage tracking, and MCP servers.

Open Multi-Agent - TypeScript-native runtime where a coordinator turns a goal into a task DAG and a deterministic scheduler runs specialized agents, with approvals, traces, evaluation, checkpoints, and resume support.

Open Session - Self-hosted server driving coding sessions in git worktrees on your own box or in isolated sandboxes, with a web UI, Slack/Linear/Plain/GitHub intake, diff and PR review, and multiple Codex and Claude subscriptions.

Open Walnut - Self-hosted web UI for coding sessions on your laptop and remote dev boxes, with a daemon on each host that keeps sessions running when SSH drops, a per-session diff of every file changed, and tasks and notes alongside. Claude Code.

open-swe - Invoked from Slack, Linear, or GitHub comments; each task runs in its own cloud sandbox and ends in a draft PR linked to the ticket.

OpenChamber - Open-source workspace for running, supervising, and reviewing AI coding work across desktop, browser, editor, and mobile, with parallel model runs and per-run worktrees.

openclaw - Your own personal AI assistant, on any OS and any platform.

openfang - Open-source agent operating system.

opengoat - Build organizations of OpenClaw agents coordinating across Codex, Claude Code, Cursor, and OpenCode. (last commit 2026-04)

OpenHands - Self-hostable control center running its own agent or driving Claude Code, Codex, and any Agent Client Protocol agent, on schedules or webhooks.

OpenHuman - Open-source personal agent harness: desktop app and Rust library with built-in memory, token compression, and instant tool search, efficient enough to run hundreds of agents on a $10 server.

OpenInstinct - iMessage assistant that drives a real browser to do chores, book tickets, and handle groceries, keeping your passwords and cards in an encrypted vault it unlocks per action. Self-hosted on your own Vercel, any model.

openkanban - Kanban board for orchestrating coding agents, rendered entirely in the terminal.

OpenMausBot - Open-source Grok Bot-style team of bots in a chat-app sidebar, where every bot is a real local agent — Claude or Codex — with its own personality, model, cloud computer, and connected apps, behind approval gates. Local-first, bring-your-own-agent.

OpenRig - YAML-defined agent team with a lead agent that runs Claude Code and Codex together as one persistent system in tmux. npm CLI.

openswarm - Local mission-control center for launching, monitoring, approving, and coordinating multiple AI agents in parallel.

OpenWorker - Open-source desktop AI coworker that delivers finished work — security review with re-scanned fixes, cloud posture audits, triaged inboxes — from specialist coworkers, with every action governed and logged. BYO model key or fully local via Ollama.

Orbi - Picks up GitHub Issues labeled ai-ready, implements each in an isolated worktree, has a separate session review the PR against the Issue's acceptance criteria, then merges only the reviewed head and cuts a tagged release. Runs on Pi with any OpenAI-compatible API or a Codex subscription.

orc - Lightweight framework that piggybacks your existing CLI setup for planning, task decomposition, worktrees, and review.

Orca - Agentic development environment for running a fleet on your own subscription, available on desktop and mobile.

OrcaReplay - Records a coding agent at the process and socket boundary so model traffic, shell exit codes, per-turn file changes and MCP JSON-RPC share one timeline, then replays the run offline with the network off or forks it from a checkpoint onto a different model.

ORCH - CLI runtime managing agents as typed teams with an explicit state machine and goals. Claude Code, Codex, Cursor.

Orchestrator - MIT-licensed macOS workspace connecting Codex execution with Kanban tasks, subagent inspection, repository browsing, and local code review; public beta for macOS 15+ using the user's own supported Codex account.

Orchestrator.inc - Desktop workspace that runs and supervises teams of coding agents from planning to merge: project-aware orchestration splits work into workers with isolated workspaces, tracked on a live Kanban with PRs, CI, and review, plus iPhone and Android apps. Claude Code, Codex, and 30+ harnesses.

ordewell - Turns one goal into an editable plan of tasks, each carrying its own runner, model and mode, then runs each task as its own agent session and passes it only when evidence of completion shows up in that session's output. Claude Code, Codex, OpenCode.

Orkas - A commander agent decomposes goals and dispatches specialists with isolated skills and memory. Claude Code, Codex, OpenCode, OpenClaw, Hermes.

OtoDock - Self-hosted "company OS" where agents work in departments, delegate to each other, and keep working unwatched on your Anthropic/OpenAI subscriptions — company map, per-agent dashboards, artifacts, meetings, and terminals. Source-available under FSL-1.1.

Ouijit - Kanban board and terminals wired together by lifecycle hooks, scripts, and a session-aware CLI, so a task runs by hand, on a script, or delegated to the agent. Per-task worktrees, optional VM sandboxing. Claude Code, Codex, Pi, OpenCode.

Ouroboros - General-purpose agent with durable identity and memory, reviewed self-modification, multi-agent coordination, and desktop and headless interfaces.

outsourcerer - Delegate coding grunt-work to other harnesses and models while your main session stays the orchestrator.

Overlay - Open-source workspace where humans and agents share context — knowledge, files, memory, connected apps — so you delegate repeatable work to agents, review what they produce, and take action through tools, provider-neutral.

ox - The team hivemind: persistent context recorded once and recalled across agents, machines, and teammates, as a Go CLI.

paperclip - Self-hosted platform where agents wake on heartbeats to claim tickets, governed by org charts, budgets, and approval gates.

pappardelle - TUI that turns a description into a Linear, Jira, or beads issue, a git worktree, a PR, and a Claude Code session beside a companion pane, wired together in a 3-pane tmux layout.

parallel-code - Desktop app running Claude Code, Codex, and Gemini CLI side by side in isolated worktrees, with a built-in diff viewer and one-click merge.

Paseo - Self-hosted daemon running agents in parallel on your own machines, driven from desktop, iOS/Android, web, or CLI, with voice control, diff review, and no telemetry or forced log-ins. Claude Code, Codex, Copilot, OpenCode, Pi.

Perch - Native macOS app in the notch for supervising parallel agent sessions: shows when one finishes or needs approval, lets you allow, deny, or reply with one key, and jumps to the exact terminal tab, cmux split, herdr pane, or Conductor workspace. Local-only, no account. Claude Code, Codex, OpenCode, Pi.

PersonalJarvis - Desktop voice and chat assistant for Windows, macOS, and Linux that runs CLI coding agents such as Claude Code, Codex, and Gemini CLI side by side in Git worktrees, with memory, scheduled routines, and any single model key or local models via Ollama.

picoclaw - Tiny and fast assistant deployable anywhere.

Podium ADE - Open-source workspace for taking ideas from conversation to coordinated work with coding agents. A shared task system lets them organize the effort while developers follow progress and change direction.

pohunek - Per-machine Rust daemon that keeps agent sessions alive across disconnects, each in its own git worktree, marks them working, blocked, or idle, and has a JSON CLI so agents can drive other sessions, across machines over NetBird or Tailscale. Codex, Claude Code, and Hermes Agent.

Pragma - Native desktop app running agent teams in parallel worktrees, each with its own branch and GPU-accelerated terminals, with a task board from prompt to PR, fan-out races that compare agents on one prompt, and a public plugin API. Desktop, web, and mobile, locally, over SSH, or in WSL. Claude Code, Codex, OpenCode, Cursor.

Proliferate - Agent IDE that runs sessions locally or in the cloud and lets you build reusable workflows from them.

Prowl - Native macOS command center for running coding agents in parallel, with vertical tabs, a live canvas view of every running session, and a command palette. Claude Code, Codex, and more.

qm - Multiplayer harness where each teammate gets an isolated workspace to run agents independently, driven from Slack or the web.

QwenPaw - Personal assistant that deploys to your own machine or the cloud and plugs into multiple chat apps. Formerly CoPaw.

Rakazo - Self-hosted platform for persistent AI teammates with their own conversations, memory, and routines, running on shared team computers or isolated private ones, reachable from web, desktop, and mobile with voice mode. Bots delegate to peer bots or short-lived subagents. BYO model and sandbox.

ralph-claude-code - Development loop for Claude Code with exit detection that recognizes when the work is actually finished.

ralph-orchestrator - Hat-based orchestration that keeps agents looping until done, as a fuller implementation of the Ralph Wiggum technique.

ralph-tui - Drives an agent through a task list autonomously, with a TUI for watching the loop.

ralphex - Executes an implementation plan autonomously with a fresh session per task, plus validation, retries, multi-phase review, and automatic commits. Claude Code, Codex.

ralphy - Bash script that loops Claude Code, Codex, OpenCode, Cursor, Qwen, or Droid until the task is done. (last commit 2026-02)

Raven - Host agent that plans a complex task as a DAG and coordinates dependencies and parallel execution across built-in research, coding, design, and on-call agents and third-party agents over ACP, CLI, or OpenAI-compatible APIs. Presets include Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, GitHub Copilot, Qwen Code, and Kimi Code.

Reemoat - Self-hosted remote control for any coding agent: run coding agents on your own machines and supervise them from anywhere, end-to-end encrypted.

ReevesAgents - TUI, Web UI, and CLI that run coding CLIs side by side in tmux windows, plus an opt-in MCP server so one agent can spawn, read, steer, and stop the others. Claude Code, Codex, OpenCode, Hermes, Kimi, DeepSeek, Qwen, Pi, Aider, and more.

remote-swe-agents - Serverless control plane on Lambda with a dedicated EC2 worker per session, triggered by issue comments, assignments, and PR reviews.

Replicas - Cloud coding-agent platform that runs Claude Code, Codex, and other agents in isolated VMs and returns pull requests from Linear, Slack, GitHub, or a dashboard.

repomon - Rust TUI that supervises a fleet across many repositories at once, in durable tmux sessions you can approve from your phone.

rho - Stays running, remembers across sessions, and checks in on its own. macOS, Linux, Android.

Roamgate - Browser and PWA client for Herdr that controls parallel terminals, monitors coding agents, and reviews files and diffs from desktop or mobile. Requires a running Herdr server. Codex, Claude Code, Kimi, Grok Build, Pi, and more.

Routa - Multi-agent coordination platform via MCP/A2A.

Rovai AI - Desktop and web workspace where persistent teams of Claude Code, Codex CLI, OpenCode, and Pi agents collaborate through shared conversations, task delegation, and collaborative memory.

Rove - TUI orchestrator that gives each task its own git worktree and branch, with sessions that survive detach or dropped SSH, a Kanban board whose cards launch sessions and get moved by agents, and a rove api for agents to dispatch tasks that report back. Claude Code, Codex, Copilot, Kimi, Pi, Gemini CLI, OpenCode, Cursor Agent, and any CLI you register.

row-bot - Local-first desktop assistant that reasons through messy context, orchestrates tools and providers, and works inside your files, repos, and channels — durable memory, scheduled tasks, voice, visible browser automation, and parent-led child agents for research, review, and implementation. Runs on Ollama or opt-in cloud models. Formerly Thoth.

rowboat - Open-source AI coworker with memory.

ruflo - Meta-harness for deploying coordinated swarms and conversational multi-agent workflows. Formerly claude-flow.

run-gemini-cli - Google's official GitHub Action, running on event or schedule triggers or on demand via @gemini-cli /review and /triage.

Runner - Native macOS and Windows app running CLI agents side by side in split panes, each keeping its own TUI in a real terminal, and putting them on one mission as a crew with a lead. Claude Code, Codex, Copilot CLI, pi.

sandbox-agent - Daemon, HTTP/SSE API, and TypeScript SDK for driving six coding agents inside E2B, Daytona, Modal, Cloudflare Containers, or Docker.

sandcastle - Orchestrate sandboxed coding agents in TypeScript with sandcastle.run().

Scalekit - Integration layer that gives agents per-user OAuth and scoped tool access to 600+ connectors and 35,000+ tools, callable from LangChain, OpenAI Agents SDK, Claude, Hermes or any MCP client.

scion - Orchestration testbed running agents in parallel isolated containers with dynamic coordination and normalized telemetry.

Sculptor - Run parallel Claude Code agents in isolated containers with a pairing mode for local sync.

shire - Persistent team workspaces with inter-agent mailboxes and a shared drive. Claude Code, OpenCode, Pi.

Sillage - Self-hosted, mobile-first web UI for driving Claude Code and Codex sessions on your own machine.

skillfold - Declares skills in YAML and pins exact revisions in a lockfile so installs are reproducible across Claude Code and Codex.

Sno Station - Local runtime where agents share one encrypted memory and a mailbox, hand a task to another agent when one hits its usage limit, and review each other's work across vendors. Codex, Claude Code, Cursor, Hermes, OpenClaw.

Solenta - Desktop app where every thread shares one local memory and the plan is your GitHub issues, with worktrees, Git review in the loop, and verify-gated completion. Claude Code, Codex, Cursor, Kimi, Grok, OpenCode.

sortie - Turns tracker tickets into agent sessions. Agent-agnostic and tracker-agnostic, as a single Go binary with SQLite persistence.

SpaceApp - Source-available (BSL 1.1), self-hosted web workspace where OpenCode, Codex, Claude Code, Gemini CLI, and other coding-agent CLIs run side by side as terminal panes in persistent rooms, with MCP servers, managed browser panes, a Room Agent for coordinating work across panes, and a one-command Docker installer (npx run-spaceapp) for Linux, macOS, and Windows 11.

Speakeasy control plane - MCP gateway for Claude Code, Cursor, Codex, and custom agents, with identity-based tool access, per-action security policies, and audit logs.

squad - Human-led AI agent teams for any project built on GitHub Copilot: repo-native specialist agents, coordinator routing, and parallel work, with persistent memory across sessions.

Sqwakie - Source-available (FSL-1.1-ALv2, converts to Apache-2.0) coordination layer for a team's coding agents across machines: agents post, reply, subscribe and ask each other from the CLI or as MCP tools over a signed, append-only team log replicated peer-to-peer (built on iroh, or over Tailscale), with a live Mission Control dashboard and kanban project boards whose cards agents can start, review and finish. Setup connects Claude Code and Codex; macOS on Apple Silicon and Linux.

sub-agents-skills - Portable Markdown definitions that route a task to a chosen backend, model, effort level, and permission set.

subtask - Claude Skill that runs your tasks through subagents in git worktrees. (last commit 2026-04)

supacode - Native macOS command center for worktree-per-agent development.

Superagent - macOS desktop app giving Claude Code and Codex a real browser to drive, an iOS Simulator to install and screenshot apps in, and a phone companion app for remote monitoring.

SuperPlane - Coordinates coding agents, source control, CI, review, approvals and feedback to turn routine backlog issues into review-ready pull requests. Supports Claude, Cursor and OpenAI.

superset - Code editor built around running many agents on your machine at once.

swarm-protocol - Headless coordination over MCP: claim work, detect file conflicts, heartbeat, and hand off across sessions. (last commit 2026-03)

Swarm-Tools - Tool for coordinating AI agents with learning capabilities.

SwarmClaw - Self-hosted AI agent runtime for autonomous agents, delegated work, schedules, provider management, and chat-platform connectors.

symphony - Turns project work into isolated autonomous runs, so teams manage the work rather than supervise the agent.

synara - GUI desktop workspace for running and managing agents across local projects.

t3code - Harness control surface available as web, mobile, and desktop app. Claude Code, Codex, Cursor, Grok Build, OpenCode.

takopi - Telegram bridge that puts Codex, Claude Code, OpenCode, and Pi sessions in a chat thread.

Tale - Runs project-board tasks in persistent sandboxes, with manager-agent delegation and deliverable review. Supports Claude Code, Codex, OpenCode, and other configured runtimes.

Talorys - Personal AI assistant that runs entirely in your own Cloudflare account: chat, durable memory, tasks, notes, and scheduled routines, deployed with one command; single-user and free-tier friendly.

taOS - Self-hosted AI agent OS where memory, conversations, agents, and files live on hardware you own, offline by default with cloud by choice, including multi-framework group chat and a desktop GUI.

TaskHandoff - Self-hosted web control plane that runs Codex sessions in isolated Docker workspaces on local and remote machines, with per-task checkouts, a diff review gate, and planner/executor/human handoff.

Taskuary - Local-first work inbox that triages email, chat, issue trackers, and scheduled reports into supervised Claude Code, Codex, Gemini, Cursor, or Copilot CLI runs, with conflict-aware queuing, live terminals, and approval-gated replies.

Tembo - Runs any coding agent in the cloud, giving each change its own computer and tracking agent work and merged results with Tembo Insights.

Tempest - Tauri desktop ADE running CLI agents in parallel isolated worktrees, with a shared local code-knowledge graph that cuts token use across sessions, plus live status and built-in diff/PR review.

termany - Terminal that keeps many agent sessions in one window, tagging each pane working/done/needs-attention from the running job rather than the shell prompt, with diffs, worktrees, port handling, remote hosts, and token cost in the same place. Claude, Codex, Gemini, Grok Build, OpenClaw, Hermes, OpenCode, Cursor, Kimi, OMP.

Threadlines - Desktop app where each thread can run in its own Git worktree beside a live browser, terminal, and source control, and a second agent can join a thread to answer questions or review the first one's changes. Claude Code, Codex, OpenCode, Cursor, Antigravity, fx, and agents from the ACP registry.

thurbox - TUI orchestrator with remote SSH sessions, inter-session messaging, and a native code-review view. Works with any CLI agent you define.

tlbx - Self-hosted browser workspace holding persistent real PTY sessions on your own machines, reachable from any browser or phone.

tmux-ide - Turns any project into a tmux IDE from a checked-in ide.yml, including preset agent-team layouts.

Tortie - Native macOS agent multiplexer with familiar IDE features: all projects in one window, agents that survive restarts, and organized terminal sessions without tmux.

toryo - Trust-based delegation with quality ratcheting that commits improvements and reverts regressions. Chains Claude Code, Aider, Gemini CLI, Ollama.

Traycer - Bring-your-own-agent workspace running many sessions in parallel with context shared across models and providers, plus agent-to-agent messaging, shareable boards, and cross-device sync.

tuios - A terminal window manager that knows what your agents are doing. Tile panes across nine workspaces in the terminal you already use. A daemon keeps sessions running when you detach and reaches your other machines. The coding agents in your panes report what they are doing, and one Inbox holds everything they are waiting on. Agent integration for claude-code, codex, gemini-cli, opencode, amp, antigravity, copilot, crush, cursor-agent, devin, droid, grok, hermes, kilo, kimi, pi, omp, qoder, qwen.

tutti - Config-driven workflows passing typed artifacts between agents, each in its own worktree.

UpComputer - Desktop, web, and PWA app for task-based self-orchestration: task tags and statuses trigger agents that run on a schedule or from a webhook, in parallel or as a queue. Claude Code, Codex, Grok, OpenCode, Cursor, and more.

vibe-kanban - Kanban board for managing AI coding agents. (last commit 2026-04)

vibe-tree - One git worktree per agent, delivered as desktop, web, and CLI.

vibecraft - RTS-style workspace for commanding coding agents.

Vicoa - Agentic IDE and AI orchestrator for running a team of coding agents from desktop, web, or mobile, with real-time sync, parallel git worktrees, and push notifications. Claude Code, Codex, OpenCode, Gemini, Cursor, GitHub Copilot, Kimi, Hermes.

Vigil - Native macOS terminal where a manager agent runs the tree — spawning workers and sub-managers, detail flowing down, summaries rolling up — while every node stays the CLI's own TUI you can take over. Claude Code, Codex, OpenCode.

Volt - Open-source agentic workspace on the VS Code core that runs agent chats side by side, each optionally in its own Git worktree, with subagents, hunk-level keep or undo of agent edits, and a Git checkpoint per turn. Claude Code, Codex, OpenCode, Cursor, Grok, Antigravity, Kimi, and any ACP agent, plus local models through Ollama.

Waku - Native macOS desktop app for working with local coding agents, keeping projects, sessions, and transcripts on your machine. Supports Amp, Claude Code, Codex CLI, Cursor CLI, Grok Build, OpenCode, and Pi.

wit - Locks individual functions rather than files via Tree-sitter, warning agents of conflicts before they write. (last commit 2026-03)

wmux - Terminal workspace app for macOS and Windows that runs the real agent CLIs in parallel, with git worktree fan-out, agent-to-agent messaging, a fleet board, and a phone companion. Supports Claude Code, Codex, Gemini CLI, and OpenCode.

wreckit - Run the Ralph Wiggum loop over your roadmap. (last commit 2026-04)

WSP - Orchestrates Claude Code, Codex, OpenCode, and Cursor across machines and cloud workspaces, syncing memory, skills, MCPs, plugins, tools, and configuration into each workspace; its desktop app, CLI, and MCP let developers or agents coordinate the same thread fleet from their preferred environment.

Xiryn - Open-source personal agent on your own machine: each agent gets its own Linux desktop in Docker, with an encrypted vault, any model under your keys, and Telegram control.

xum - Desktop app for isolated, parallel agentic development.

Yardlet - Native macOS app that runs each agent's own CLI and sign-in side by side, keeping sessions in the agent's own store, with handoff between tasks, usage limits across accounts, shared MCP connectors, and a browser the agents drive. Claude Code, Codex, OpenCode, Cursor Agent, Antigravity CLI, Pi.

Yardsort - Cross-platform Tauri desktop app giving each task its own git worktree and real terminal, with live per-file diffs, agent hand-offs, YAML workflows, and terminals that keep running after the window closes.

YYLO - Command-line orchestrator for coding agents with typed task, validation, merge, and release-readiness boundaries: each task runs in a dedicated branch and worktree, and a risk-based merge queue reviews the result with receipt-backed changes. Pi and Codex subagents.

Zaivern Code - Cross-platform Rust desktop cockpit for running Claude Code, Codex, Gemini CLI, and 30+ coding agents in parallel, with fleet monitoring, mobile control, and line-level ownership to prevent merge conflicts.

zclaw - Complete personal assistant in 888 KiB, running on an ESP32 with GPIO, cron, and custom tools.

zeroclaw - Fast, small, fully autonomous assistant infrastructure in Rust, deployable anywhere.

Zeron - Cross-device control plane for coding agents, syncing sessions across machines and keeping agents running on an always-on daemon. Claude Code, Codex, Cursor, Grok, Hermes, Pi.

zuse - Chat-first desktop app wrapping Claude Code, Codex, Grok, Gemini, Cursor, and OpenCode in persistent sessions. macOS and Linux.

Agent Sandboxes

Why Sandbox Agents

• Untrusted code. Model-generated code can be wrong or malicious, and may be steered by prompt injection.
• Blast radius. Limit filesystem, network, credential, and process access to what the task needs.
• Reproducibility. Fresh, disposable environments make agent runs repeatable and easy to discard.
• Parallelism. Many agents can run concurrently without stepping on each other.

Choosing an Isolation Level

Level	Mechanism	Boundary	Typical startup	Trade-off
Process	seccomp, Landlock, Seatbelt, bubblewrap	Shared host kernel, restricted syscalls and paths	Milliseconds	Lightest; kernel exploits escape
Container	Docker, Podman, OCI runtimes	Shared host kernel, namespaces and cgroups	Sub-second	Common default; weaker than a VM
User-space kernel	gVisor	Intercepted syscalls	Sub-second	Smaller kernel attack surface, some syscall overhead and compatibility gaps
MicroVM	Firecracker, Cloud Hypervisor, Kata Containers	Hardware virtualization, separate guest kernel	Typically well under a second	Strongest common boundary; more moving parts
Full VM	KVM, cloud VMs	Hardware virtualization	Seconds or more	Heaviest; most compatible

Pick the weakest boundary you can defend against your threat model. Code from untrusted users or multi-tenant workloads generally calls for a microVM or user-space kernel; a single developer running their own agent often does fine with a container or a process-level sandbox.

Hosted Sandbox Platforms

Managed services that give agents on-demand isolated environments through an API or SDK.

AgentSphere - MicroVM sandboxes for LLM code execution, with MCP integration.

Blaxel - Lightweight VM sandboxes that enter standby when idle while preserving the filesystem, memory, and running processes, with TypeScript, Python, and Go SDKs.

BlueRock Agent Sandbox - Commercial agent sandbox with MCP visibility and action-level tracing.

boat.dev - Ubuntu VMs for agents with Docker, a browser, and common dev tools preinstalled, controlled through a CLI, HTTP API, and Python and TypeScript SDKs, with a virtual desktop and fast forking, pausing, and snapshotting of machines.

BoxCompute - Full Linux VMs on KubeVirt with root access, an HTTP API, a CLI, and TypeScript and Python SDKs.

Cloudflare Sandbox SDK - Run commands, manage files, and expose services in isolated Linux environments from Cloudflare Workers, using Containers that each run in their own VM and Durable Objects for sandbox identity.

CodeSandbox SDK - Programmable, persistent development environments for coding-agent workflows.

Cognitora - Firecracker microVMs with hardware-level isolation.

CreateOS - MicroVMs with pause-to-snapshot, fork-based branching, and private overlay networking for multi-agent systems.

Daytona - Programmable sandboxes that run as containers by default, with options for Linux and Windows VMs and GPUs, snapshots, shared persistent volumes, and Python, TypeScript, Ruby, Go, and Java SDKs.

Deno Sandboxes - Sandboxes from Deno with millisecond boot times.

E2B - Open-source Firecracker microVM sandboxes for coding, code-interpreter, and computer-use agents, with templates, memory and filesystem snapshots, pause and resume, and bring-your-own-cloud on its Enterprise plan.

exe.dev - Persistent Linux VMs with root access, Docker, and systemd, reachable over SSH or a browser interface, with a built-in web coding agent called Shelley.

Fly.io Sprites - Persistent Firecracker VMs with exec sessions and checkpoint and restore.

Freestyle - Hardware-virtualized Linux VMs with root access, Docker Compose, eBPF, FUSE, and nested virtualization, built for long-running agent workspaces with persistent terminals.

InstaBox - Full Linux VMs for long-running agents, each with its own kernel, root access, Docker, and systemd, plus a desktop and browser for computer use and the ability to fork running machines.

LangSmith Sandboxes - Full-root microVM sandboxes with filesystem snapshots, opt-in memory capture, and an auth proxy that keeps credentials outside the guest.

Lizard Sandboxes - Managed Firecracker microVM sandboxes with snapshots, live forks, and TypeScript and Python SDKs.

Modal Sandboxes - gVisor-isolated containers inside Modal's serverless platform for running untrusted code, with custom Images, snapshots, persistent Volumes, and optional egress restrictions.

Northflank Sandboxes - Managed sandboxes, or deployment into your own cloud or Kubernetes cluster.

Novita Sandbox - Agent runtime sandboxes with SDK decorators and one-click configuration.

OmniRun - Firecracker microVM sandboxes with desktop GUI control, end-to-end encryption, and TypeScript and Python SDKs.

Runloop Devboxes - VM-isolated development environments for software-engineering agents, with Blueprints, disk snapshots, suspend and resume, network policies, and benchmarking infrastructure.

Runtime - Firecracker microVMs that pause and wake while keeping memory and processes, with snapshots, forks, and an MCP server.

Sandbox as a Service - Full cloud VMs with 24-hour sessions, public preview URLs that open no inbound port on the sandbox, a REST API, and an MCP server.

shellbox.dev - SSH-accessible Linux boxes.

Tenki Sandbox - Hardware-isolated Linux VMs with warm-start sessions, snapshot and fork, and multi-language SDKs.

Tensorlake - Sandboxes for running untrusted LLM-generated code, with snapshots, suspend and resume, fan-out to many parallel instances, CLI and Python and TypeScript SDKs, and on-premises or bring-your-own-cloud deployment.

Upstash Box - Agent-oriented sandbox environments where the agent runs inside the sandbox.

Vercel Sandbox - Firecracker microVM Linux environments with root access, JavaScript and Python SDKs, network policy control, and persistent filesystems by default.

YepCode Run - Serverless JavaScript and Python execution in sandboxes.

Self-Hosted Sandbox Runtimes

Open-source runtimes you operate on your own hardware or cloud.

agent-vm - Per-project libkrun microVMs that bind-mount the project and swap real OAuth tokens for placeholders through a TLS-intercept proxy; Linux with /dev/kvm.

AgentFS - Copy-on-write filesystem sandboxing that isolates an agent's file changes from the original source tree.

agentsafe - Per-task microVM sandbox for AI agents.

AgentVM - Node.js library that runs WebAssembly-based Alpine Linux in worker threads for shell execution.

AIO Sandbox - All-in-one container with a browser, terminal, VS Code, Jupyter, and an MCP server.

amla-sandbox - WebAssembly sandbox with capability enforcement against shell escapes and unauthorized access.

Arrakis - MicroVM isolation with snapshots and backtracking.

Bouvet - Rust-based sandbox for running agent code.

boxed - Code-execution engine for untrusted agent code across Docker, Firecracker, and WebAssembly.

BoxLite - Embeddable VM-style sandboxing with snapshots and persistent state.

BunkerVM - Firecracker microVMs that record each command, rewind to any step, and compare agent runs.

bVisor - Embedded bash sandbox inspired by gVisor.

Capsule - WebAssembly runners for sandboxed code execution.

Cleanroom - Self-hosted microVM sandbox with deny-by-default egress and credential proxying.

conch - WebAssembly-based bash sandbox for agent command execution.

CubeSandbox - KVM microVM sandboxes built on RustVMM with copy-on-write snapshots, eBPF network isolation, and an E2B-compatible SDK.

Enclave - JavaScript sandbox that prevents code injection and prototype pollution.

ERA - Local sandboxing in krunvm microVMs with a container-like workflow and optional Cloudflare Workers deployment.

Eryx - Rust library that runs Python in a WebAssembly sandbox through Wasmtime.

Firecracker - KVM-based microVM monitor built for multi-tenant serverless workloads, and the basis of several agent sandbox platforms.

Flintlock - MicroVM lifecycle management backed by containerd, for building higher-level solutions.

Gondolin - QEMU-based microVMs with programmatic network and filesystem control.

gVisor - Application kernel that implements Linux syscalls in user space, usable as an OCI runtime (runsc).

HyperAgent - Hyperlight micro-VM runtime in which model-written JavaScript handlers run with no filesystem, network, or shell access unless granted through plugins.

K7 - Self-hosted lightweight VM sandbox infrastructure with an API and SDK.

Kata Containers - OCI-compatible container runtime that runs each pod or container in a lightweight VM.

Kilntainers - MCP-oriented sandbox runtime backed by Docker, Podman, microVMs, or WebAssembly.

Kubernetes Agent Sandbox - Kubernetes APIs for agent workloads with pluggable isolation backends such as gVisor and Kata.

llm-sandbox - Python library that runs LLM-generated code in Docker, Kubernetes, or Podman with configurable security.

LocalSandbox - Python SDK with a SQLite-backed virtual filesystem for running bash and Python.

Matchlock - CLI that runs agents in ephemeral microVMs (Firecracker on Linux, Virtualization.framework on macOS) with network allowlisting and host-side secret injection.

MCP Runner - Multi-tenant MCP server platform using Docker with the gVisor runtime.

microsandbox - Self-hosted microVM sandboxes for running untrusted code from AI agents.

Monty - Minimal Python interpreter written in Rust with microsecond startup and strict capability controls, with no OS boundary.

nervos - Firecracker microVM sandbox for AI agents.

Netclode - Self-hosted cloud coding agent that uses Kata Containers with Cloud Hypervisor microVMs.

OpenShell - NVIDIA's policy-enforced container runtime with declarative YAML policies for filesystem (Landlock), network (OPA proxy), process (seccomp), and inference access.

PythonSafeEval - Python execution inside an nsjail process jail within Docker containers.

SandBase Harness - Self-hosted agent runtime with per-session Docker and Kubernetes sandboxes, MCP tool permissions, approvals, and audit and replay.

SandboxAI - Runtime for running AI-generated code in sandboxes across clouds.

Sandboxer - Forkable sandbox server for LLMs and agents.

smolvm - Hardware-isolated VMs that boot in under 200 ms using Hypervisor.framework, KVM, or WHP, pull OCI images without a Docker daemon, and pack into a single file.

SmolVM - Disposable VMs for agents on Firecracker, QEMU, or libkrun, with read-only host mounts by default, snapshots, egress controls, and a browser sandbox.

Wassette - MCP server runtime that executes WebAssembly components with isolated tools.

zapcode - Sandboxed TypeScript execution engine for AI tools.

Local Sandboxes for Coding Agents

Tools that confine a coding agent running on your own machine.

agentbox - Containerized agent sandbox with network firewalling and privilege dropping.

Agent Safehouse - Deny-first macOS Seatbelt profile system for local coding agents.

agent-sandbox.nix - Nix wrappers for running AI CLIs with explicit package and network allowances.

ai-jail - Sandbox using bubblewrap, Landlock, and seccomp on Linux and Seatbelt on macOS, with a tmpfs home, copy-on-write overlays, and a lockdown mode.

Amazing Sandbox - Local sandbox for running third-party tools and AI agents.

bashkit4j - In-JVM sandboxed bash with reimplemented commands on an in-memory filesystem and allowlisted host mounts, with no containers or VMs (Java 17+).

bromure - macOS app that runs disposable Linux VMs destroyed on window close, with a host-side proxy that swaps fake credentials for real ones.

cage - Runs coding agents in isolated Docker containers on macOS or Linux.

cco - Launcher that picks a local sandbox backend for coding agents.

Chamber - Runs Claude or Codex in ephemeral Tart-based macOS VMs.

ClaudeBox - Docker-based Claude Code environment with persistent state and network allowlists.

claude-code-devcontainer - Hardened devcontainer template for running Claude Code.

ClodPod - macOS VM workflow that maps host projects into a guest environment.

CodeRunner - Local sandbox for running LLM-generated code on macOS using Apple containers and MCP.

codex-lockbox - Docker sandbox that runs Codex CLI behind firewall rules.

cplt - Seatbelt and Landlock sandbox for coding agents, with the policy committed to the repository.

Dev Containers - Open specification for running a project's development environment in a container, commonly used to confine agents to a repository.

Docker Sandboxes - Docker's isolated environments for running coding agents locally.

drydock - Per-task throwaway VMs on Apple's container runtime with deny-by-default egress, budget-capped tokens, and only a git diff leaving the sandbox.

EdgeBox - Local sandbox that exposes a desktop GUI to the agent.

Fence - Lightweight CLI sandbox that restricts network and filesystem access using OS-native tools.

Greywall - Linux sandbox with live network control and visibility.

hort - Daemonless Rust tool that gives each agent a disposable git worktree and in-process OCI container, with an egress allowlist.

Landrun - Landlock-based sandboxing without root.

Leash - Policy enforcement wrapper for coding agents with Cedar-based rules and real-time monitoring.

lima-devbox - Lima-based VM development sandbox for Mac.

locki - Lima VM with Incus containers and a command bridge that filters git operations, so agents write only to namespaced branches.

machine - One isolated Lima VM per GitHub project on macOS, with no host filesystem mounted and SSH agent forwarding that keeps private keys on the host.

Microbox - Lightweight ephemeral Linux sandboxes.

Mudroom - macOS app and CLI that runs coding agents in Linux micro-VMs on a copy-on-write clone of the project, behind a network allowlist proxy, with per-hunk diff review.

nilbox - Desktop app that runs a full Linux VM per project, with a host proxy that swaps dummy tokens for real ones and human-in-the-loop domain gating.

nixcage - Nix environment sandboxing with bubblewrap on Linux and sandbox-exec on macOS.

nono - Capability-based sandbox using Landlock on Linux and Seatbelt on macOS, with snapshots, atomic rollback, and an audit trail.

opencode-seatbelt - macOS Seatbelt sandbox that confines the OpenCode process and hides secrets matched by .ocignore.

packnplay - Docker wrapper for AI coding assistants with automatic git worktrees and devcontainer support.

Pent - Native OS process sandbox for untrusted commands.

runbox - Minimal container-like sandbox written in C.

sand - CLI that runs agents in Apple container VMs on APFS copy-on-write clones of your project.

sandbox-run - bubblewrap wrapper for per-project Linux command isolation.

sandbox-runtime - Anthropic's lightweight OS-level sandbox that enforces filesystem and network restrictions on arbitrary processes without a container.

sandbox-shell - macOS Seatbelt shell wrapper with deny-by-default filesystem access.

sandclaude - Opinionated Docker wrapper for Claude Code.

sandlock - Confines untrusted code with Landlock, seccomp-bpf, and seccomp user notification.

sandnix - Nix module that wraps programs with Landlock or sandbox-exec.

SandVault - Runs agents in a separate macOS user account hardened with sandbox-exec.

sbox - Small isolation-first sandbox.

shai - Sandboxing shell for AI coding agents.

sucoder - Contains coding agents with Unix user permissions.

treebeard - Ephemeral git worktree sandbox with copy-on-write handling and optional network restrictions.

Vibe - Zero-configuration Debian Linux VMs on macOS using Virtualization.framework, for LLM agents.

vibebin - Incus/LXC platform for persistent self-hosted coding-agent sandboxes.

vibebox - Local macOS sandbox for AI agents.

yolo-cage - Sandbox aimed at preventing data exfiltration by coding agents.

yoloAI - Local runner that can use macOS Seatbelt, Tart, or Docker, with a review-and-apply workflow.

Yolobox - Runs coding agents in Docker containers that keep them away from your home directory.

Isolation Primitives

Low-level building blocks used to build sandboxes.

bubblewrap - Unprivileged Linux sandboxing tool built on namespaces.

Cloud Hypervisor - Rust-based virtual machine monitor used as a microVM backend, including by Kata Containers.

firecracker-go-sdk - Go SDK for building Firecracker-backed runtimes.

Firejail - Mature Linux application sandbox using namespaces and seccomp.

island - Landlock-based Linux sandbox CLI.

Landlock - Linux security module that lets unprivileged processes restrict their own filesystem and network access.

libkrun - Library for running processes in lightweight, KVM-backed microVMs.

Minijail - Containment launcher and library used in ChromeOS and Android.

sacre_bleu - Seccomp and Landlock policy generation and enforcement suite for Linux binaries.

seccomp - Linux syscall filtering used by container runtimes and sandboxes.

syd - Userspace syscall-intercepting Linux sandbox.

WebAssembly System Interface (WASI) - Capability-based system interface for running WebAssembly modules with explicit grants.

Wasmtime - Standalone WebAssembly runtime with WASI support, usable for sandboxing untrusted plugins and code.

Browser Sandboxes

Isolated browsers for agents that navigate and act on the web.

Browserbase - Hosted headless browsers for AI agents and web automation.

Playwright - Browser automation library often run inside containers or VMs to isolate agent browsing.

Sandbox Abstraction Layers

Unified APIs that run the same code across several sandbox providers.

ComputeSDK - Universal API across multiple cloud sandbox providers, with automatic provider detection.

VibeKit - SDK that runs coding agents on providers such as E2B, Daytona, and Modal.

Agent Memory

Memory layers, servers, and benchmarks for giving AI agents persistent memory. Merged from cxxz/awesome-agent-memory, tfatykhov/awesome-agent-memory, and TeleAI-UAGI/Awesome-Agent-Memory. Research papers and surveys are left in those lists.

Memory Layers and Frameworks

A-Mem - Zettelkasten-style create/link/revise operations with ChromaDB indexing and automatic memory evolution.

A3M Router - Multi-model LLM router with persistent memory (MemoryTree), cross-session context-window management, conversation memory with semantic recall, and ObsidianVault integration.

ActiveMemoryIndex - Dual store of verbatim timestamped turns and atomic first-person facts, retrieved in the same register; #3, Agent Memory Leaderboard (academic textual, 2026-08).

Agent Knowledge Cycle - Six-phase knowledge cycle specification (ADRs, JSON schemas, reference implementation) that turns coding-agent sessions into persistent skills, rules, and memory.

agent-memory-doctor - Boot-time integrity checker for agent memory files and SQLite session stores: fingerprint and hash checks, size and freshness limits, archive verification; CLI and GitHub Action.

agent-memory-recall - Read-only Python CLI searching Hermes Agent's conversation store and notes, wiki, memory and skill files; --home or --roots target other layouts or artifact folders.

Agentic Task System - Agent-native context layer over your existing task app (TickTick; Notion/Obsidian planned), exposing hybrid retrieval over tasks/notes to agents via a CLI with pluggable storage adapters.

Agno - Full-stack multi-agent framework with built-in Storage/Memory drivers, small footprint, and fast stateful agents.

alethech - Verifiable agent continuity in Python: Ed25519-signed memory commits in a hash-linked DAG, identity-preserving key rotation, encrypted portable history; local-first, zero-LLM.

AML Memory MVP - Evidence-only, typo-tolerant retriever over English and CJK text using SQLite FTS5, character n-grams, and conversation-neighbor expansion; #10, Agent Memory Leaderboard (academic textual, 2026-08).

archon-memory-core - Local-first agent memory with nightly consolidation, active forgetting, and salience scoring.

AtMem - Local-first agent memory with governed retrieval, provenance, lifecycle controls, delegated context delivery, execution evidence, SQLite storage, MCP, and an audit dashboard.

Belief Context Graph - Confidence-aware belief graph organizing long-horizon agent context into trackable, updatable belief states; includes SDK, graph-building tools, visualization UI, and agent benchmark.

Big Agentic Brain - Self-hosted shared memory for an organization's agents: one container on SQLite, BM25 search boosted by agents' reactions, and agent-to-agent messages; MCP or HTTP API.

birkin-mnemosyne - Stdlib-only Python memory for agents: Markdown vault with BM25, Korean bigrams and usage decay; model curation passes through a deterministic safety-clamping executor; optional MCP server.

chamnan - Repository-local context for coding agents: an architecture index, impact map, and decision records committed beside the code.

Chronicle Memory - Evidence-only memory over SQLite with a hybrid lexical scorer adding phrase, temporal, and session-diversity bonuses; #7, Agent Memory Leaderboard (academic textual, 2026-08).

ChronoHybridMem - Evidence-only textual memory over SQLite FTS5 with optional LLM fact extraction and multi-route candidate recall; #5, Agent Memory Leaderboard (academic textual, 2026-08).

claude-memory-tidy - Maintenance layer for always-loaded agent memory files: deterministic budget guard, orphan-note coverage, and verbatim folding into warm sub-indexes, guarding against silent truncation.

CodeAlmanac - Repo-local Markdown wiki for AI coding agents that preserves project conversations, decisions, and implementation context.

Cognee - Extract-Cognify-Load pipeline that turns conversations/files into graph + vector memory to replace/augment RAG with relationship-aware recall.

CommonGround Kernel - PostgreSQL-backed shared work-record substrate for human-agent and multi-agent systems, with durable handoff facts, causal lineage, and pull-first recovery across runtimes.

Compartment - Offline, encrypted-at-rest vector memory for agents via MCP server, Python, or CLI; AEAD-encrypted embeddings, hybrid recall, per-record crypto-shred deletion, hash-chained audit log.

daimon - Session-continuity memory for coding agents: session-end checkpoints become next-session briefings with items tagged verbatim or inferred; human-ratified rules can block shell commands.

Data Olympus - Governed project memory for AI coding agents: agents propose learnings, humans promote them, and MCP retrieval serves only in-force knowledge after validity and supersession checks.

elephant - Claude Code plugin keeping per-repo memory in a committed ELEPHANT.md plus a global cross-repo file; hooks load both at session start and prompt saves.

engram (by FBISiri) - Go memory service on Qdrant with write-time dedup and importance gating, type-based TTL decay, reflection into insights, and MCP plus REST interfaces.

Engramory - General-purpose long-term memory layer for AI agents: one markdown file per memory, a size-capped pointer index read every session, and a read-only validator.

EverOS (part of EverMind) - Toolkit for building, evaluating, and integrating long-term memory in self-evolving agents.

ExperienceNet - Self-hosted experience network for agents: search and write real technical attempts (problem/conditions/action/outcome), lexical + semantic hybrid retrieval over PostgreSQL/pgvector, gap capture, reuse feedback.

FeedRecall - Local-first MCP memory for saved social discoveries, with source dates, project relevance, evidence lifecycle, timelines, and bounded recall for coding agents.

Fidelis Memory - Local-first memory for coding agents: MCP recall returns original passages verbatim via vector search, with an explicit BM25/RRF hybrid mode; no generative LLM in retrieval.

FlowGrid AML Retriever - Deterministic, evidence-first Add/Search retriever that stores every original message and returns ranked, traceable source evidence; #8, Agent Memory Leaderboard (academic textual, 2026-08).

FluctlightDB - Embedded database engine for AI agents with experience()/activate() API and reproducible LoCoMo evaluation.

Fraise - In-memory temporal graph database for agents, queried with remember/recall verbs over HTTP or MCP; hybrid text, graph and optional vector retrieval; no persistence yet (2026-10).

gbrain - Garry's opinionated OpenClaw/Hermes agent brain.

GoodMemory - Local-first, auditable memory layer for AI agents and coding hosts, with durable SQLite, embedding-free recall, MCP access, and opt-in governed writeback.

Graphiti - Bi-temporal knowledge graph: edges carry validity intervals and are invalidated, not overwritten, so superseded facts remain queryable with time bounds. The closest production analogue to Memory Transactions, Versioning & Recovery.

Graphmem - Local-first memory for coding agents in Rust: scoped memories and an entity graph in SQLite, recalled via local embeddings plus Personalized PageRank; MCP server.

hermeneutic - Turns corrections from AI agent logs into guidance for similar tasks: local semantic memory with prompt-context hooks and response checks.

Hindsight - Consolidation as an explicit policy layer over four levers — importance, merge, decay, eviction — instead of an unbounded append log. Industry framing already cited in Adjacent Research; paper: arXiv:2512.12818.

HMS (Holographic Memory System) - Long-term memory QA framework that wraps OpenAI clients with automatic recall and retain, PostgreSQL-backed, evaluated on LongMemEval.

Honcho - Memory as a representation of a person, not a transcript: background reasoning maintains per-peer models, queried through a dialectic API rather than similarity search.

Hybrid Memory Search - Local hybrid-retrieval memory service with per-user isolation, synchronous embedding on write, and fused BM25/dense ranking; #4, Agent Memory Leaderboard (academic textual, 2026-08).

IHMT - Local MCP memory for coding agents: a tree of plain-text leaves and JSON summaries, with dated facts and OUTDATED/AMBIGUOUS notices, shared across agents.

inspeximus (formerly mnemo) - Zero-dependency memory layer and MCP server with value-ranked recall, per-type decay, keyed supersession, revert-based correction, signed provenance, tamper-evident receipts, and cross-store erasure.

InvMem - Vanilla RAG baseline (chunking, embeddings, FAISS/SQLite vector store) behind a synchronous Add/Search API; #1, Agent Memory Leaderboard (academic textual, 2026-08).

kannaka-memory - Rust agent memory as a wave-interference medium: phase-coded wavefronts, bilateral hemispheres, dream consolidation and forgetting, NATS swarm sync; CLI and MCP plugin.

kith - Relationship memory between agents on SQLite: append-only observations derive trust, reliability, and sentiment views with per-entry visibility scopes.

Lians agent memory - Bitemporal agent memory with deterministic supersession, point-in-time recall, MCP access, audit trails, and local SQLite or PostgreSQL storage.

Lint-AI - Agent memory and semantic review engine with lexical, temporal, and graph-aware retrieval across conversations, documents, code, and agent sessions.

LLMSlim - Context-compression library whose no-LLM memory stores turns verbatim in SQLite or Postgres and recalls them, whole where they fit, within a token budget; stdio MCP.

LWC - Agent-operated persistent memory CLI with source-cited Wiki pages, full-text search, document graphs, and CodeGraph indexes for cross-session project recall.

Mem0 - “Universal memory layer” for short/long-term + semantic/episodic memory, with a local-first dashboard and broad framework integrations.

Mem9 - Local private memory hub for OpenClaw and similar coding agents.

Memanto - Typed semantic memory with remember/recall/answer operations and information-theoretic retrieval.

Memary - Human-memory-inspired layer with persona-aware graphs and multi-graph support (FalkorDB/Neo4j; local or hosted LLMs).

memclaw (Felo) - Persistent project memory for AI coding agents — isolated per-project workspaces, a web dashboard to review what the agent remembers, and team collaboration.

MemEngine - Unified, modular library with many pluggable memory models and automatic config selection for local/remote runs.

memgres - Versioned document memory for AI agents over one Postgres; lexical or semantic recall, diff-based history, git-blame line attribution, GDPR-erasable, multi-tenant via MCP/HTTP.

MemMachine - Universal memory layer that lets agents learn/store/recall user data across sessions, building evolving user profiles. Supports Working (Short-Term), Persistent (Long-Term), and Personalized (Profile) memories with developer-friendly APIs (Python SDK, REST, and MCP). Persists episodic memory in a graph DB and profile memory in an SQL DB.

Memobase - User profile-based long-term memory for AI chatbot applications.

memonto - Ontology/knowledge-graph memory that extracts entities/relations and exposes graph queries; can run ephemeral or persist to triple/vector stores.

Memori - Open-source memory engine for LLMs and agents with entity extraction, auto-categorization, memory promotion, and multi-agent sync. Supports temporal retention policies, retrieval tuning, and cross-agent context exchange.

Memorix - Local-first cross-agent memory layer for coding agents via MCP — SQLite-backed project memory with observation, reasoning, and git-derived fact types, plus task-lensed context briefs.

memory-lancedb-pro - Enhanced LanceDB memory plugin for OpenClaw.

MemoryAgent - FastAPI + ChromaDB memory system with local sentence-transformers embeddings and similarity-based write deduplication; #9 as LLLMemoryAgent, Agent Memory Leaderboard (academic textual, 2026-08).

MemoryBear - Memory framework providing human-like episodic and semantic recall to AI agents.

MemoryOS - OS-like memory stack with short/mid/long-term layers and plug-and-play storage/retrieval; exportable via tools.

MemOS - "Memory OS": a MemCube abstraction unifying plaintext, activation (KV), and parameter memory, with scheduling and cross-task reuse between them. Rare in treating KV-cache and long-term store as one substrate.

Memov - Git-based, traceable memory layer for Claude Code.

MemTether - Shared SQLite memory hub for AI clients over MCP, CLI and REST: corrections supersede rather than delete, bi-temporal timestamps, hash-anchored audit log, human conflict adjudication.

MemU - Companion-focused memory that organizes/links/evolves memories, adds adaptive forgetting, and emphasizes accuracy + cost efficiency.

Mi-Memory - Lifecycle memory framework for personal assistant agents from Xiaomi's Darwin Agent team; multi-source user state with provenance, editable correction and forgetting, device-adaptive deployment.

MIRIX - Multi-agent personal assistant that captures on-screen activity and consolidates it into structured memory.

MisakaNet - Git-based distributed swarm memory; agents share lessons across nodes via GitHub Issues.

Mnemory - Multi-type agent memory (facts, preferences, episodic) with TTLs, user/agent scoping, and an MCP server.

Mnemosyne (by 28naem-del) - Local-first TypeScript agent memory in one SQLite file; memories keep source evidence, corrections retire recorded dependents, exact replay and bisect in 3.0 pre-release; MCP, CLI.

Mnemosyne (by ElonAug7) - Memory engine for OpenClaw and Hermes: JSONL and Markdown layers ranked by weighted importance, recency, keyword and hit-frequency scoring; offline by default, DashScope embeddings opt-in.

Mnemoverse - Hosted long-term memory for agents over MCP and REST; rating a recalled memory as helpful or misleading re-ranks what comes back next; MIT-licensed MCP server.

MoobFS - Experimental Linux filesystem for agent-memory storage, with typed extended attributes and permission-scoped queries; developed with AI assistance, for disposable-VM evaluation.

myc - Local task-and-memory layer for coding agents: decision oplog with hybrid search, session/repo-scoped recall, PreCompact hook saving the episode before compaction; Bun + SQLite.

Nemori - Self-organising long-term memory substrate for agentic LLM workflows. Nemori segments multi-turn conversations into topic-consistent episodes, distils durable semantic knowledge, and exposes a unified search surface for downstream reasoning. The system uses insights from Event Segmentation Theory and predictive processing and provides production-ready concurrency, caching and pluggable storage options.

notebook.py - Single-file Python tool for Claude Code transcript memory, stored as editable Markdown with source references and retained history of retired entries.

O-Mem - Omni memory system for personalized, long‑horizon, self‑evolving agents. It views memory as an active user‑modelling process: it continually extracts and updates user persona attributes, event records, and topic‑indexed messages. This enables dynamic user profiling, a three‑layer hierarchical memory (persona, event and message), user‑centric retrieval, and interaction‑time scaling. O‑Mem includes an evaluation suite and exposes modular APIs under the Apache‑2.0 license.

OMEGA - MCP server exposing 25 memory tools for AI coding agents.

Omnigraph - Object-storage-native graph engine for agent memory with git-style branch/merge workflows.

OpenMemory Engine - Self-hosted, sectorized semantic memory engine with hierarchical storage, auto decay, and explainable recall graphs; integrates with LangGraph, Mem0, and MCP tools.

OpenViking - Memory, knowledge, and skills in one virtual filesystem (viking://): scoped search over a directory subtree instead of a flat vector pool, and L0 abstract / L1 overview / L2 source tiers so agents judge relevance before opening content. Committing a session archives it and extracts memories as inspectable, editable Markdown. Backed by the peer-reviewed VikingMem Memory Base Management System (VLDB 2026 ). Headline LoCoMo / τ²-bench gains are vendor-run with Doubao models.

PackRat - Auto-learning codebook compression that shrinks agent context files while keeping them LLM-readable.

Panella - Self-hosted governed memory over MCP; agent writes become durable only after human approval with verifiable receipts; Apache-2.0.

Persistent AI Memory System - Persistent, searchable memory plus tool-usage logs, deduping/self-reflection, and cross-conversation sync.

PowerMem - Persistent, self-evolving memory for AI agents — hybrid vector/full-text/graph retrieval with LLM-driven extraction, Ebbinghaus-style decay, and two-layer Experience + Skill distillation; from the OceanBase team.

projectmem - Local-first, event-sourced memory for AI coding agents: an append-only event log served via MCP, plus a pre-commit gate that warns before repeating a failed fix.

Puppyone - Filesystem-shaped agent memory with auto-versioning, per-agent ACLs, and data connectors; accessible via MCP/REST/CLI.

RCLL - Self-hosted shared memory for a fleet of agents: topic rooms, L0–L3 depth, Postgres/pgvector; the read path invokes no language model. Fork of Hindsight.

ReFind - Memory retriever that plans iterative searches over a conversation-level BM25 index and returns contextual evidence blocks; #2, Agent Memory Leaderboard (academic textual, 2026-08).

ReMe - Remember Me, Refine Me. A modular memory management kit that unifies personal, task, and tool memories for agents. Features refinement cycles, temporal prioritization, and Pydantic-backed schemas to ensure memory coherence and relevance.

Remnic - Local-first Markdown memory shared across coding agents and MCP clients, with per-result provenance, correction workflows, and the MemCorrect benchmark.

RetainDB - Local-first agent memory with noise filtering, typed facts, reuse-based reinforcement, and BM25 + vector + graph retrieval with RRF and reranking; Apache-2.0 core, BSL-1.1 server.

Second Me - Personal AI trained on the user to represent them across applications.

Selvedge - Local decision memory for coding agents: records code decisions, rejected approaches and revisit conditions in SQLite; retrieved through MCP or CLI.

skillmem - Skill memory for Claude Code and Codex agents: records how tasks were solved, recalls them, reinforces what works, decays the rest; SQLite + FTS5 MCP server.

sqlite-graph-memory - Graph RAG memory for agents over a markdown vault: dense retrieval, hand-curated wikilink 1-hop expansion, cross-encoder rerank, per-turn SQLite ledger.

Statewave - Open-source memory runtime for AI agents serving reproducible, provenance-tagged context bundles instead of query-time retrieval; self-hosted on Postgres + pgvector with Python/TypeScript SDKs.

Synap - Long-term memory layer that extracts facts, preferences, episodes, and temporal events from conversations; integrates with most major agent frameworks.

Talamus - Local-first agent memory that stores source-grounded Markdown, preserves bitemporal history and provenance, and exposes search, recall, and review-gated correction through MCP.

taOSmd - Local-first, offline agent memory: an append-only transcript yields a typed temporal knowledge graph with source-grounded, verifier-checked facts and hybrid retrieval, tuned for small local models.

Task Memory Engine - Structured task-level memory engine combining hierarchical trees and rollback-aware buffers to track multi-step reasoning; enables state reconstruction and planning with minimal context tokens.

TeleMem - API-compatible high-performance drop-in replacement for Mem0 (import telemem as mem0); listed as an unranked sub-item of Mem0 per the drop-in replacement convention. Maintainer-affiliated.

TencentDB Agent Memory - Fully local long-term memory for AI agents via a 4-tier progressive pipeline, with zero external API dependencies.

Verified Memory Vault - Obsidian vault doubling as Claude Code memory: deterministic health-score linter (undated entries, duplicates, dead links) plus a git pre-commit hook refusing mass deletions.

Wenlan - Local-first AI knowledge base and LLM wiki that distills agent work into source-cited pages and serves them to MCP clients.

widemem-ai - Lightweight memory layer with importance scoring, temporal decay, and 3-tier hierarchy.

YYLO Ledger - Git-native task and Record store for coding-agent workflows: reviewable current state, append-only history, dependency-aware work, and bounded queries.

ZenBrain - Neuroscience-inspired 7-layer memory architecture for autonomous agents in zero-dependency TypeScript, with FSRS spaced repetition, Hebbian learning, and sleep-cycle consolidation.

Zep - Temporal knowledge graph memory (Graphiti engine) with bi-temporal facts and hybrid retrieval (graph + semantic + keyword).

溯忆 (Suyi) - Dual-temporal memory engine for AI agents — SQLite-backed, zero-dependency, Ebbinghaus-decayed fact storage with skill crystallization.

Local-First and Coding-Agent Memory

agentmemory - Full lifecycle memory for coding agents: confidence scoring, decay and consolidation, knowledge graph, hybrid search, ~20 agent adapters. Headline ranking claims are self-reported.

Caura - Governed shared memory for agent fleets: trust tiers, keystone policies, audit trails, multi-tenant scoping. The implementation counterpart to Memory Trust & Integrity and Multi-Agent Memory.

causal-memory - Local-first Rust MCP server (also CLI + PyO3 bindings) where the store is one SQLite file holding facts, temporal state, and typed decision→outcome edges (caused / enabled / prevented). Spreading activation runs both ways — prevented edges carry negative activation, a GABA analogue — alongside Hebbian co-occurrence, Q-value dynamics, write-time gating, and immutable SWR-style consolidation. Reproducible benchmark harnesses (CausalEval, LoCoMo, LongMemEval) live in-repo; Hermes Agent provider plugin included.

deja-vu - No write path: indexes the session transcripts 34 coding agents already write locally (lexical by default; optional deja embed may send text to an external embedding API) and serves them to any of the others — including pre-install history, so no cold start. Read-side mechanisms: outcome-aware ranking (a session that ended in a fix outranks one that gave up), redaction at ingest, per-project trust policy, forget/unforget. LoCoMo/LongMemEval drivers in-repo.

Engram - Agent-agnostic Go binary — SQLite + FTS5, MCP/HTTP/CLI/TUI, explicit conflict handling. Deterministic lexical recall as a deliberate counter-position to embedding everything (cf. ReFind in Retrieval & Recall).

Hyperconsciousness - Rust knowledge store with signed, encrypted append-only records and scoped, expiring grants for MCP access. Delegated grants cannot widen scope, add actions, or outlive their parent. Governance at the retrieval boundary; does not sandbox processes running as the owner. Developer alpha; no independent security audit.

kgai - Append-only, content-addressed decision log for dev teams: every change is a new event that supersedes the prior one through an explicit link with a reason, rejected paths stay queryable (temporal versioning), recall returns only decisions in force. Deterministic graph projection, lexical recall with no embeddings, and per-writer shard sync over the team's own S3 bucket (no server). Repo-supplied config is gated behind an explicit trust approval (governance). Claude Code plugin plus a Go CLI.

Lemmalog - Memory as a deductive database: a Rust stratified-Datalog engine in which LLM-extracted base facts are bi-temporal and carry confidence × provenance semiring annotations. Rules derive closures, temporal projections, and contradiction candidates incrementally per turn; why() returns proof trees, retraction recomputes only dependents, and what_if runs hypotheticals with byte-identical restore. Ships as an MCP server.

Lockstep - Shared decision memory for teams of coding agents and product managers: an append-only, CAS-versioned decision ledger where decisions are drafted, reviewed and ratified before agents receive them, with rationale and rejected options kept. Briefs each agent over MCP before it acts. Optional opt-in check flags changed code that may contradict an accepted decision. Hosted service (getlockstep.dev) by default; self-hostable via Docker.

memsearch - Markdown files as the source of truth, Milvus for hybrid retrieval, typed episodic/procedural memory. Human-readable store = auditable memory.

mengram - Typed semantic / episodic / procedural memory where procedures are derived from recorded failures — one of the few OSS systems implementing the failure → procedure loop from Skill & Procedural Memory.

Mnemon - Single Go binary, four-graph knowledge store with intent-aware recall, importance decay, and automatic deduplication. No API keys, one setup command.

Nocturne Memory - Rollbackable, visually inspectable graph memory server for MCP agents — edits are reversible operations, not blind writes. The practical counterpart to MemTX/ChronoMem-style recovery.

recall - Reads and writes Claude Code's auto memory (Markdown files with wiki-links) over MCP or from code, so Codex, Cursor and other agents share the same memory. Zero dependencies.

Synapse - Markdown-authoritative local memory with write-once imports and provenance-bearing agent note proposals that require human approval. SQLite FTS5 and the linked-page graph are disposable indexes; MCP exposes selective retrieval instead of injecting the whole vault.

Vestige - Local-first Rust MCP server combining FSRS-6 decay, spreading activation, contradiction inspection, active suppression, Receipt Lock, and an inspectable dashboard. Built for causal recall — the quiet change that broke today, not the lookalike.

Memory Modules for Agent Frameworks

Ars Contexta - A second brain for your agent. A Claude Code plugin that generates complete knowledge systems from conversation — you describe how you think and work, and the engine derives a cognitive architecture (folder structure, context files, processing pipeline, hooks, navigation maps, and note templates) tailored to your domain and backed by 249 research claims. No templates, no configuration — just conversation.

AutoGen - Memory - Provides a Memory protocol (e.g., ListMemory) and official notebooks showing long-term memory with Zep and Mem0 in conversational agents.

CrewAI - Memory - Adds short-term (RAG) and long-term stores (e.g., SQLite backed) so crews retain insights across executions and reuse them later.

LangGraph + MongoDB Store - Introduces a persistent document memory layer for LangGraph, combining vector and document stores for scalable long-term retention.

LangMem - SDK that gives agents long-term, semantic memory with tools to store/search memories in LangGraph stores, plus a managed service and templates.

LlamaIndex - Agent Memory - Unified APIs for short- and long-term memory, including composable memory so agents can combine multiple sources. Recent updates improve long/short-term blocks.

Semantic Kernel - Memory Plugin - Embeddings-based memory plugin (e.g., TextMemoryPlugin) to save/recall short/long-term info across agents in.NET/JS/py SK apps.

smolagents - Memory - Exposes a first-class agent memory you can inspect/replay/modify; supports step callbacks for dynamic memory policies.

MCP Memory Servers and Tools

Basic Memory - Local-first Markdown knowledge base exposed via MCP; bi-directional human/LLM editing with simple, file-backed persistence.

MCP Memory Service (doobidoo) - Universal MCP memory with semantic search, natural-language time filters, and storage options (SQLite-vec/Chroma/Cloudflare).

mcp-memory (Puliczek) - Cloudflare-backed MCP memory with D1 + vector search, namespaces, and rate-limited, TLS-secured endpoints.

MCP-Titan - Experimental neural memory engine integrating online vector processing and TensorFlow.js learning loops, enabling live memory update and auto-retention control.

memory (HamzaFarhan) - Minimal knowledge-graph MCP server (entities/relations/observations) with JSON persistence and flexible search modes.

Memory MCP Server (Swift) - Lightweight MCP server for entity/relation memory graphs with JSON storage and a simple CLI.

memory-mcp (JamesANZ) - MCP memory for conversation logging, context-window caching, relevance scoring, and MongoDB storage.

OpenMemory MCP - Mem0’s local-only MCP server that centralizes cross-tool memory with a unified dashboard.

Redis Agent Memory Server - Redis-powered memory with REST + MCP, two-tier memory (session/long-term), configurable extraction, and pluggable vector backends.

Supermemory MCP - Graph memory service implementing MCP context sharing, cross-app recall, and relationship graphs for multi-agent sessions.

Reinforcement-Learning Training for Memory

Mem-α - RL framework that teaches agents how to build and manage complex memory systems through interaction and feedback. Agents process sequential information, learn to extract and store relevant content, and update core/episodic/semantic memory components; rewards derive from downstream question-answering accuracy.

MEM1 - End-to-end RL that learns a compact internal state for constant-memory long-horizon agents; integrates new observations while discarding redundancy to improve efficiency.

MemAgent - RL-trained long-context agent with a memory mechanism that enables arbitrarily long inputs within fixed windows; RLVR-based training and linear-time scaling, shown to extrapolate to multi-million-token tasks with minimal loss.

Memento - Memory-based online RL over a memory-augmented MDP with a neural case-selection policy; planner–executor loop reuses past trajectories so agents learn without fine-tuning the base LLM.

MemEvolve - Meta-evolution framework that jointly evolves an agent’s memory base and memory architecture via a dual-loop process, enabling the memory system itself (not just contents) to improve over time. Includes automated multi-round tournament evolution with candidate generation, evaluation, and selection; supports optional Pareto multi-objective selection.

Memory-R1 - the paper (code not yet publicly available) proposes an RL framework where a Memory Manager learns to add, update or delete memory entries and an Answer Agent learns to select relevant entries. Both agents are trained with PPO and GRPO to actively manage and utilise an external memory bank.

MemSearcher - RL-driven search agent that maintains a compact memory, fusing each query with memory to generate reasoning traces, perform search actions, and update memory to keep only task-relevant information (stabilizing context length across long multi-turn runs). Uses multi-context GRPO end-to-end RL to jointly optimize reasoning, search, and memory management.

Benchmarks and Evaluation Harnesses

DolphinBench - Memory measured through task completion over ~500k-token persona histories. Every task is verified to succeed with the history and fail without it, and submissions must report cost and latency with accuracy. Built by a memory vendor.

GateMem - Memory governance under multiple principals sharing one store: utility, access control, and active forgetting measured together instead of accuracy alone.

HaluMem - Operation-level hallucination benchmark: scores extraction, updating, and answering separately, exposing errors that end-to-end QA accuracy hides. License is declared by README badge only — no LICENSE file in the repo; NC-ND terms forbid commercial use and derivatives, so treat it as read-only unless you clear it with the authors.

LoCoMo - Very long-term conversation benchmark (ACL 2024 ). Widely used dataset; frozen — last push Aug 2024, cite the data, don't expect maintenance.

LongMemEval - ICLR 2025. 500 questions across five long-term memory abilities over long interactive histories. The de-facto standard — and the number most vendor claims cite.

LongMemEval-V2 - Official successor, released 2026, addressing saturation and contamination in the original.

Mem-Gallery - ACL 2026 Main. Multimodal long-term conversational memory for MLLM agents. Last push Jan 2026.

MemoryData - Unified harness — 4 benchmark families, 22 method presets, one runtime — built specifically to make heterogeneous memory systems comparable. Directly attacks the fragmentation problem Evaluation & Benchmarks documents.

STATE-Bench - Microsoft. Memory-agnostic enterprise workflows measuring whether an agent improves with experience, not whether it recalls a fact. Blog write-up in Adjacent Research.

Hosted and Closed-Source Memory Products

AccInt - Local-first MCP Work Model for coding agents that retrieves scored memory, records actions, and credits real outcomes; engine is a closed-source binary.

Agent QA - QA agent that retains persistent test memory to reuse prior runs and self-heal natural-language web and mobile tests.

Agentage Memory - Remote MCP memory server (OAuth 2.1 + PKCE + DCR) giving Claude, Cursor, and ChatGPT one shared markdown memory mirrored locally as files you own.

brethof-brain - Memory for 20 coding-agent harnesses via hooks: session-start brief, per-prompt recall, archived turns, decisions with date and reason; local or hosted store, vendor-side processing.

ByteRover - LLM-curated hierarchical context tree for coding agents, with git-like branching, cloud sync, and MCP; formerly Cipher.

Context Mode - Context-window optimization for AI coding agents: diverts large tool outputs into a locally searchable store and persists session memory across platforms via MCP and hooks.

ContextStream - Hosted MCP context layer for coding agents: persistent decisions and lessons, semantic code search, post-compaction recovery; MIT-licensed Rust client, hosted backend closed-source.

Enhanciar - Hosted company brain for teams and agents: reads Slack, Gmail, Drive, Notion, Jira, Linear, GitHub, Zendesk and Postgres, answers with a link to the source, and is reachable from Claude and Cursor over a remote MCP server; closed source, paid, bring your own AI key.

Firekeep - Self-hosted shared memory, working context, coordination, and evidence for Claude Code, Codex, Kiro, OpenCode, and other MCP clients.

Marvnor - Hosted structured memory API for AI agents, with answers grounded in stored records, conflict detection, in-place correction, and targeted deletion.

Membase - Memory layer shared by Claude, ChatGPT, Cursor and custom agents via MCP or MIT-licensed Python/TypeScript SDKs; hosted, or local on a compiled engine.

MemoraX - Memory layer for long-horizon agents from MemoraX AI; core system is API-only; #1, Agent Memory Leaderboard (industry textual, 2026-08).

MemoraX Code - Coding-agent memory product—not a text-chatbot memory layer—that carries engineering experience, repository knowledge, preferences, and procedures across tasks and sessions.

MemorySync - Hosted memory API for AI apps: stores, searches and deletes memories per end user via REST, Python and Node.js SDKs, or remote MCP server.

Mnemosyne OS - Desktop memory app (Windows, macOS, Linux); watched folders feed separate vaults; vector and local BM25 search; MIT MCP server; BEAM 49.2% at 10M, self-reported.

Monolithos - Personal agent app (macOS, iOS, Windows); memory is a local Markdown vault; vendor servers route model calls; opt-in cloud copy enables read-only MCP recall.

Monolithos Robot Brain - Long-term memory and experience layer for embodied AI; public Alpha under an evaluation license, core ships as a compiled package; HTTP API and Python SDK.

Moraine Home - Local-first memory workbench for personal agents and companions: hybrid keyword/vector retrieval, human-and-agent review of candidates, reversible consolidation, timelines, and MCP/HTTP interfaces.

Okto Neuron - Local-first knowledge graph memory from Markdown notes and agent writes; a user-configured LLM extracts claims; MCP answers can cite file path, byte range, content hash.

ORANO - Consumer app that distills saved Reels, videos, articles, and PDFs into projects and memory facts that the user's agent reads over a read-only MCP server.

past.dev - Temporal memory API: stores timestamped text with its source; recall returns facts current at a given time and what each replaced; REST and remote MCP.

Perseus Vault (formerly Mimir) - Local MCP memory server as a single Rust binary: SQLite FTS5 plus vector hybrid search, AES-256-GCM at rest; GitHub source repository not publicly accessible (2026-09).

RE-call - Postgres plus pgvector memory retrieval for AI agents, with provenance, trust verdicts, tenant isolation, MCP access, and abstention when evidence is insufficient.

Remio - Local-first personal knowledge base that indexes files, webpages, recordings, notes, emails, and messages for agent retrieval via search and RAG.

Remnant - Hosted collective memory over MCP: agents search other agents' published technical experience, inspect provenance, record outcomes, and contribute lessons through a separately authorized connection.

screenpipe - Local-first work memory that captures screen, audio, input, browser, and meeting context for search and agent retrieval.

Sentra - Organization-wide memory layer for teams and agents: ingests meetings, mail, tickets, and repositories into a bi-temporal fact graph served over REST and MCP.

Supermemory - Memory API, hosted or free self-hosted; SDKs, MCP server, and dashboard are MIT, but the memory engine ships only as a prebuilt binary.

TokenRip - Hosted MCP workspace shared by Claude, ChatGPT, Codex and Cursor: versioned files, tasks and pinned decisions, each change recording which agent made it; MIT CLI.

Wontopos (Tablet 2) - Memory API with no language model in the retrieval path; paper-reported 95.7% LongMemEval-S, 95.2% recall@5 over 70 language pairs, and BEAM-1M 67.5% with published harness.

Zambo - Hosted MCP tool gateway with saved-fact recall across AI clients, session handover between them, and a public SHA-256 receipt per call.

More AI Development Tools

Tools outside the main lists above. Format: - [Tool Name](https://example.com/) - Brief description.

Agent Orchestrators

Tools and frameworks for orchestrating AI coding agents.

Parallel Agent Runners

• 1code - UI for Claude Code with local and remote agent execution.
• 5dive - Run a company of named AI agents on a server you own, each with its own model, memory, and role. Agents share an org chart and backlog, hand work to each other, and escalate to a human over Telegram. Multi-runtime: Claude Code, Codex, Grok, Antigravity, and opencode.
• agentbox - Run multiple coding agents in parallel, each teleported into its own sandboxed box with local Docker or cloud VMs via Hetzner, Daytona, Vercel, or E2B. Works with Claude Code, Codex, and OpenCode.
• agent-deck - Terminal session manager for AI coding agents.
• agent-kanban - Agent-first kanban board with leader-worker model, cryptographic agent identity, and multi-runtime support for Claude Code, Codex, and Gemini CLI.
• agent-manager - Terminal UI that runs coding-agent CLIs side by side in persistent tmux sessions, with optional per-session git worktrees and diff review.
• agent-of-empires - Terminal session manager for AI coding agents on Linux and macOS.
• agent-orchestrator - Agentic orchestrator for parallel coding agents.
• agenttier - Kubernetes-native runtime that runs each AI coding agent in its own Pod and PVC sandbox, with default-deny NetworkPolicy and a streaming SSE invoke API.
• aGiTrack - Terminal wrapper for Claude Code, Codex, and OpenCode that turns each agent turn into a git commit, recording the prompt, model, and token cost in the commit message, with a local dashboard over the resulting history.
• AGX - Local-first agent orchestrator with parallel execution, wake-work-sleep checkpointing, and human-in-the-loop gates.
• ai-maestro - Dashboard for orchestrating Claude, Aider, and Cursor agents across machines.
• aizen - macOS workspace for managing git worktrees with integrated agent sessions.
• amux - TUI for easily running parallel coding agents.
• Aperant - Autonomous multi-session AI coding.
• automaker - Autonomous AI development studio.
• bernstein - Deterministic orchestrator that spawns parallel AI coding agents, verifies with tests, and auto-commits.
• Cezar - Open-source orchestrator and agentic development environment for running Claude Code, Codex, OpenCode, Pi and other coding agents in parallel, locally or on your own server.
• claude_code_bridge - Real-time multi-AI collaboration.
• Claude Command Center - Local dashboard for spawning, monitoring, and resuming parallel Claude Code, Codex, Cursor, Antigravity, and Kilo Code sessions.
• claude-squad - Manage multiple AI terminal agents in the background.
• clave - Native macOS app for running multiple Claude Code sessions in parallel with split and grid layouts, session groups, SSH remote sessions, and usage analytics.
• clideck - WhatsApp-like dashboard for managing multiple AI coding agents in one browser window.
• cmux - Open-source platform for running multiple coding agents in parallel.
• Codealong - Open-source desktop app for macOS and Linux that tracks every Claude Code, Codex, OpenCode, Antigravity and Cursor session on your machine, grouped by repo, worktree and PR, with a floating bar for approvals and replies and plan usage per account.
• CodeNomad - Command center for AI coding workflows.
• CodexMonitor - Orchestrate multiple Codex agents across local workspaces.
• collaborator - A place to create with agents.
• Conductor - Mac app for running parallel Claude Code and Codex agents in isolated git worktrees.
• constellagent - macOS app for running multiple AI agents with their own terminal, editor, and git worktree.
• crystal - Run multiple Codex and Claude Code sessions in parallel git worktrees.
• dmux - Parallel agents with tmux and worktrees.
• dorothy - Desktop app to orchestrate multiple AI CLI agents with automations, Kanban management, and MCP servers.
• emdash - Run multiple coding agents in parallel.
• ghast - Multitask with multiple terminals.
• happy - Open-source (MIT) app to orchestrate Claude Code, Codex and other agents from mobile and web, reusing the subscriptions you already pay for.
• herdr - Agent-aware terminal multiplexer with persistent workspaces, tabs, panes, and status detection for CLI coding agents.
• humanlayer - Get AI coding agents to solve hard problems in complex codebases.
• ivy-tendril - Open-source AI coding orchestrator that manages Claude Code, Codex, Antigravity, Copilot, and OpenCode through a plan-based lifecycle with verification gates, self-improving memory, and human-in-the-loop checkpoints.
• jean - Desktop and web app for orchestrating coding agents across projects and git worktrees.
• lalph - LLM agent orchestrator driven by your chosen source of issues.
• multica - Agent-first kanban board with multi-runtime support.
• mux - Desktop app for isolated, parallel agentic development.
• nimbalyst - Open-source visual workspace for building with Codex and Claude Code, including parallel sessions, git worktrees, kanban, and visual editing.
• Opcode - An open-source desktop GUI for Claude Code (formerly Claudia) for managing sessions, custom agents, usage tracking, and MCP servers.
• openkanban - TUI kanban board for orchestrating AI coding agents.
• Open Walnut - Self-hosted web console for Claude Code on your laptop and remote dev boxes, with a daemon per machine that keeps sessions running when SSH drops, one page for every session, and a per-session diff.
• Orbi - Takes labeled GitHub issues to reviewed pull requests in isolated worktrees, merges only reviewed changes, and cuts tagged releases.
• Orca - IDE for running multiple CLI coding agents side-by-side across isolated git worktrees.
• outsourcerer - Delegate coding grunt-work to other harnesses and models while your main session stays the orchestrator.
• parallel-code - Desktop app for orchestrating multiple AI coding agents simultaneously in isolated git worktrees with a built-in diff viewer and one-click merge.
• pohunek - Per-machine daemon that keeps Codex, Claude Code, and Hermes Agent sessions alive across disconnects, shows whether each is working, blocked, or idle, and has a JSON CLI so agents can drive other sessions.
• Proliferate - Open-source local and cloud agent IDE for running Claude Code, Codex, Gemini CLI, and other coding agents in parallel across isolated workspaces.
• Rove - An agent multiplexer for the terminal that runs coding agents on parallel tasks with isolated worktrees and persistent sessions.
• Sculptor - Run parallel Claude Code agents in isolated containers with a pairing mode for local sync.
• Sillage - Self-hosted, mobile-first web UI for driving Claude Code and Codex sessions on your own machine.
• sortie - Turns issue tracker tickets into autonomous coding agent sessions.
• subtask - Claude Skill to do tasks with subagents in Git worktrees.
• supacode - Native macOS coding agent orchestrator.
• superset - Terminal built for coding agents.
• symphony - Turns project work into isolated, autonomous implementation runs.
• tempest - Runs Claude Code, Codex, Gemini, and other CLI agents in parallel while cutting token and tool-call usage.
• thurbox - Multi-session TUI orchestrator for many coding-agent CLIs in persistent tmux sessions, with git worktree isolation, remote SSH sessions, inter-session messaging, and a native code-review view.
• tmux-ide - Tmux-powered terminal IDE with ide.yml layouts, agent-team templates, and Claude Code integration.
• tutti - Multi-agent orchestration CLI with config-driven workflows, git worktree isolation, and typed artifact flow between agents.
• vibecraft - RTS-style workspace for managing AI coding agents.
• vibe-kanban - Kanban board for managing AI coding agents.
• vibe-tree - Vibe code with Claude in parallel git worktrees.
• yylo - CLI orchestrator that runs each coding-agent task in its own branch and worktree, with validation boundaries and a risk-based merge queue.

Multi-Agent Swarms

• Agent Teams - Desktop app for giving high-level commands to autonomous AI agent teams across Claude, Codex, and OpenCode, with inter-agent messaging, Kanban task management, and built-in code review.
• antfarm - Build your agent team in OpenClaw with one command.
• automata - Agent swarming organization system.
• BMAD Method - Agile framework of specialized agent personas (analyst, architect, developer, QA) for planning and building with coding agents.
• centaur - Self-hosted team agent platform with Slack-native conversations, Kubernetes sandboxes, shared tools, and durable workflows.
• claude-flow - Deploy multi-agent swarms with coordinated workflows.
• clawe - Multi-agent coordination system for OpenClaw agents.
• ClawTeam - Agent swarm intelligence system.
• CompanyHelm - Distributed multi-agent orchestrator with task management and agent-to-agent conversations.
• Fusion - Multi-node, multi-platform agent orchestrator with a kanban board, plan-review-execute workflow gates, per-task git worktrees, and hierarchical missions.
• gastown - Multi-agent orchestration system with persistent work tracking.
• gnap - Git-native agent protocol that coordinates multiple agents through a shared git repo acting as a persistent task board.
• guild - Shared context, memory, and task coordination across AI coding agents.
• hcom - Connect AI coding agents so they can message, watch, and spawn each other across terminals.
• Hephaestus - Open Agent OS for Claude Code, Codex, and Cursor with a meta-agent builder, A2A Hub routing, local ontology, and governed memory and security gates.
• kodo - Autonomous multi-agent coding orchestrator that directs Claude Code, Codex, and Gemini CLI agents through work cycles with independent verification.
• loki-mode - Autonomous SDLC orchestrator with specialized agents, swarms, quality gates, blind code review, and multi-provider support.
• loom - Infrastructure for evolutionary software where autonomous loops evolve products.
• maestro-orchestrate - Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code with specialist subagents, parallel execution, and persistent sessions.
• multi-agent-shogun - Samurai-inspired tmux orchestrator for running up to 10 parallel AI coding agents with zero coordination API cost.
• openfang - Open-source Agent Operating System.
• opengoat - Build AI autonomous organizations of OpenClaw agents.
• orc - Hierarchical multi-agent orchestrator that coordinates AI coding agents through planning, task decomposition, isolated worktrees, and review pipelines.
• ORCH - CLI runtime for managing Claude Code, Codex, and Cursor as typed agent teams with state machine, goals, and TUI.
• Orkas - Local-first desktop workspace where a commander agent coordinates specialist agents and runs Claude Code, Codex, OpenCode, and Cline.
• paperclip - Orchestration for zero-human companies.
• scion - Multi-agent orchestration testbed that runs AI agents in parallel isolated containers with separate workspaces, dynamic coordination, and normalized telemetry.
• shire - Persistent workspaces for AI agent teams with inter-agent mailboxes, shared drive, and full context preservation.
• skillfold - Configuration language and compiler for multi-agent AI pipelines.
• swarm-protocol - Headless coordination layer exposed as an MCP server for claiming work, detecting file conflicts, heartbeats, and handoffs across agent sessions.
• wit - Coordination protocol that locks specific functions with Tree-sitter AST parsing so agents can declare intents, acquire symbol-level locks, and get conflict warnings.

Autonomous Loop Runners

• fractal - Open-source runtime for bounded hierarchical coding-agent loops with recursive delegation, isolated Git worktrees, persistent SQLite state, and live operator controls.
• LoopTroop - Local GUI orchestrator for long-running AI coding tasks with council planning, OpenCode execution in isolated git worktrees, and recovery loops.
• MartinLoop - Control plane for AI coding agents with hard budget stops, verifier gates, rollback evidence, and inspectable run receipts.
• ralph-claude-code - Autonomous AI development loop for Claude Code with intelligent exit detection.
• ralph-orchestrator - Hat-based orchestration that keeps agents in a loop until done.
• ralph-tui - Orchestrate AI coding agents to work through task lists autonomously.
• ralphy - Runs AI agents on tasks until done.
• toryo - Intelligent agent orchestrator with trust-based delegation, quality ratcheting, and Ralph Loop retries.
• wreckit - Run Ralph Wiggum Loop over your roadmap.

Personal Assistants

AI assistants that bridge to messaging platforms and other interfaces.

• accomplish - Open-source AI coworker that lives on your desktop.
• aeon - Autonomous agent framework that runs unattended on GitHub Actions, with skills, quality scoring, self-healing, persistent memory, and reactive triggers.
• assistant - Panel-based personal assistant with a plugin architecture for productivity workflows.
• babyagi3 - Minimal AI agent you configure once, then run through natural language.
• ClawWork - OpenClaw as your AI coworker.
• CoPaw - Personal AI assistant.
• ghostclaw - AI agent that lives on your computer and works for you.
• hermes-agent - Agent that grows with you.
• ironclaw - OpenClaw-inspired implementation in Rust focused on privacy and security.
• lemon - Local-first assistant and coding agent system.
• leon - Open-source personal assistant with voice and text interfaces.
• lettabot - Personal AI assistant with memory.
• LionClaw - Secure-first local AI assistant with durable sessions and installable skills.
• lobsterai - 24/7 all-scenario AI agent.
• mercury - Personal AI assistant that lives where you chat.
• MetaClaw - Personal agent that learns and evolves through conversation.
• nanobot - Ultra-lightweight personal AI assistant.
• nanoclaw - Lightweight alternative to OpenClaw that runs in Apple containers for security.
• NemoClaw - NVIDIA plugin for secure installation of OpenClaw.
• nullclaw - Fast, small, and fully autonomous AI assistant infrastructure.
• openclaw - Personal AI assistant.
• piclaw - Pi-based general-purpose agent.
• picoclaw - Ultra-efficient AI assistant.
• rho - AI agent that stays running, remembers across sessions, and checks in on its own.
• rowboat - Open-source AI coworker with memory.
• takopi - Telegram bridge for Codex, Claude Code, OpenCode, and Pi.
• zclaw - Minimal AI personal assistant for ESP32.
• zeroclaw - Fast, small, and fully autonomous AI assistant infrastructure.

Agent Extensions

MCP servers, skills, plugins, context tools, and workflow frameworks that extend coding agents.

• agent-qa - A self-improving QA agent for natural-language web and mobile tests with run memory, UI-change adaptation, and regression detection.
• Agentik - A hosted MCP gateway that gives coding agents such as Claude, Codex, and Cursor 3,500+ third-party tools through one connection, with a price shown before each call.
• agentskill.sh - A directory of 44k+ skills for Claude Code, Cursor, and Codex with two-layer security scanning and one-command installation via the /learn skill.
• agenttrace - A local-first TUI for inspecting AI coding agent sessions across Claude Code, Codex CLI, Gemini CLI, Aider, Cursor exports, Hermes, OpenCode, Kimi, and Copilot-style logs, surfacing cost, cache usage, failures, latency, anomalies, health gates, and diffs.
• agy-powerline - Fast, configurable statusline for Google Antigravity CLI (agy) with live Gemini 5h/7d quota meters, pace markers, context usage, and interactive TUI editor.
• anthropics/skills - Anthropic's public repository of Agent Skills for Claude.
• Antigravity Link - VS Code extension that bridges mobile devices to Google's Antigravity IDE (a Claude-powered VS Code fork). Mirror active AI chat sessions on your phone, send messages, upload files, stop AI generation, and automate workflows via a local HTTP API or 9 MCP tools. Listed in the official MCP Registry.
• Archon - An open-source harness builder for AI coding that makes agent workflows deterministic and repeatable.
• Browser Use - An open-source Python library for building AI browser agents, with a hosted cloud of stealth browsers and an agent API.
• BurnRate - Local-first AI coding cost analytics. Tracks Claude Code, Cursor, Codex, Copilot, Windsurf, Cline, and Aider. Cost breakdowns, 23 optimization rules, rate limit monitoring, provider comparison, and PDF reports.
• Chrome DevTools MCP - An MCP server that gives coding agents Chrome DevTools access for debugging, performance traces, network inspection, and browser automation.
• claude-mem - A plugin that captures what your coding agent does across sessions and injects relevant context back into future sessions.
• claude-plugins-official - Anthropic's official, managed directory of high-quality Claude Code plugins.
• Claude Task Master - An open-source AI task management system that turns a PRD into dependency-aware tasks for coding agents in Cursor, Claude Code, Windsurf, and other MCP clients.
• Clogmeter - A free browser tool that weighs AGENTS.md, CLAUDE.md, Cursor rules and skill files in tokens, finds duplicates and conflicting rules, and exports a trimmed copy.
• CocoIndex Code - An Apache-2.0 code-search CLI and MCP server that uses Tree-sitter-based chunking and semantic search to retrieve code snippets for coding agents.
• code2prompt - An open-source CLI that converts a codebase into a single LLM prompt with a source tree, templating, and token counting.
• codex-profiles - An open-source MIT Bash CLI helper for switching OpenAI Codex CLI/Desktop accounts using isolated CODEX_HOME profiles, with Homebrew install and no token copying.
• Conduit8 - A CLI registry for discovering, installing, and managing Claude Code skills with one-command installation directly to ~/.claude/skills/.
• Constitution Lint Action - A GitHub Action and pre-commit hook that lints CLAUDE.md-style AI agent constitution files for missing operational guardrails (authority order, injection-defense, spend limits, escalation path, secrets handling), catching gaps in CI before an unattended coding agent runs into them.
• Context7 - An MCP server from Upstash that supplies coding agents with up-to-date, version-specific library documentation and code examples.
• CurlShot - A screenshot API with a remote MCP server (take_screenshot, list_devices) so coding agents can capture web pages as PNG, JPEG, WebP, PDF or scrolling video; also exposes an OpenAPI 3.1 spec and llms.txt. Free tier available.
• deed.page - A static-site host for coding agents: one HTTP PUT or the remote MCP server at https://deed.page/mcp publishes an HTML file or folder to a permanent https://<slug>.deed.page URL, with an open-source skill for Claude Code, Codex, Cursor, and Gemini CLI.
• Desktop Commander - An MCP server that gives Claude and other agents terminal control, file system search, and diff-based file editing.
• Dude Toldya - An open-source plugin for Claude Code and Codex that quotes your own past corrections back to the agent before it answers, reports what you correct most, and gives the orchestrator model-selection guidance for subagent calls.
• Find MCP - An MCP server for discovering other MCP servers, searching 17,000+ entries synced from the official MCP registry via remote Streamable HTTP or stdio.
• GitHub MCP Server - GitHub's official MCP server for letting coding agents work with repositories, issues, pull requests, and Actions.
• Gitingest - Turns any Git repository into a prompt-friendly text digest for LLMs, available as a website, CLI, and Python package.
• gsd-pi - A meta-prompting, context engineering, and spec-driven development system that lets agents work autonomously for long periods without losing the big picture.
• Keenable - A web search and page-fetch MCP server for coding agents, with site and publish-date filters and pages returned as markdown. Works without an API key on a shared public tier.
• MCP Config Doctor - A browser-local diagnostic for supported Codex TOML, Gemini CLI JSON, and VS Code JSONC MCP client configurations; it checks static configuration shape and secret/env risks without claiming runtime server health.
• MCP Servers - The official collection of reference Model Context Protocol server implementations.
• Mnemoverse - MIT-licensed MCP server for agent memory, backed by a hosted engine that re-ranks recall from reported outcomes rather than similarity alone, with one key shared across Claude Code, Cursor, VS Code, and ChatGPT.
• MyMCPTools - A searchable directory of MCP servers, also available as an MCP server, with reachability and tool-schema drift checks for servers that expose a remote endpoint.
• notabene - Renders repository Markdown and MDX as a navigable documentation site with anchored comments, storing comments and journals in git-readable JSON alongside a protocol agents can follow to propose or apply the corresponding edits to the Markdown source.
• Oh My Android - An open-source macOS app with a built-in MCP server that lets AI coding agents see and drive the Android Emulator and adb devices: screenshots and UI tree in dp, taps and swipes, logcat, dark mode, font scale, and RTL.
• OpenSpec - An open-source spec-driven development workflow that aligns humans and AI coding assistants on specs before code is written.
• Playwright MCP - Microsoft's MCP server that gives coding agents a real browser for testing and verifying their own work.
• repo-forensics - Offline security scanner for AI-agent repos, skills, plugins, and MCP servers; flags prompt injection, credential theft, and manifest drift before install.
• Repomix - An open-source tool that packs an entire repository into a single AI-friendly file, with token counts, secret scanning, and an MCP server.
• Repowise - An open-source codebase intelligence tool for AI coding agents that indexes repos into dependency graphs, git history, auto-generated docs, and architectural decisions via 7 MCP tools.
• SeaGOAT - A local semantic codebase search tool that uses vector embeddings for context-aware code search.
• Serena - An open-source coding agent toolkit that gives LLMs semantic, LSP-based code retrieval and editing tools through MCP.
• sharable.link - A free Claude skill that publishes HTML outputs to clean, shareable public URLs. One /share command turns dashboards, reports, and landing pages into links anyone can open — no account needed.
• SkillHey - Curated directory of agent skills for Claude Code, Codex, and Cursor, browsable by category in nine languages.
• Spec Kit - GitHub's open-source toolkit for spec-driven development, guiding coding agents from specification to plan, tasks, and implementation.
• Stagehand - An open-source SDK from Browserbase for extracting data and interacting with websites using AI and code.
• subagent-tuner - Claude Code mod that lets developers choose the model and reasoning effort of each subagent, by asking first, by task-kind recommendation, or from a saved default.
• Superagent - An open-source macOS desktop app that gives Claude Code and Codex a real browser to drive, an iOS Simulator to install and screenshot apps in, and a phone companion app for remote monitoring.
• SuperClaude - A configuration framework that extends Claude Code with specialized commands, personas, and development workflows.
• Superpowers - An agentic skills framework and software development methodology for coding agents.
• Tessl - A spec-driven development platform and registry of usage specs that help coding agents use libraries correctly.
• token-optimizer - Context and token-cost optimizer for coding agents that finds wasted tokens, survives compaction, and fights context-quality decay across Claude Code, Codex, OpenCode, and OpenClaw.
• toprank - An open-source (MIT) Claude Code plugin with 9 SEO and Google Ads skills. Connects Google Search Console, PageSpeed Insights, and the Google Ads API to audit traffic, ship meta tag and schema markup fixes, and manage ad campaigns directly from Claude Code.
• Tree Ring Memory - Local-first memory lifecycle framework for AI coding agents with Rust CLI/TUI, SQLite/FTS recall, forgetting, audit, and adapter hooks.
• UI Verify - Visual testing for coding agents: the agent sees screenshot diffs of its UI changes over MCP, from your existing Storybook, Playwright or Vitest tests.
• usage - A macOS menu bar and Windows system tray app that monitors Claude Code, Codex, and Antigravity quota, with burn rate estimates and locally generated usage reports.
• workkit - Claude Code plugin that runs GitHub Issues as the work pipeline: each issue moves through labeled stages from spec to ship, worker subagents write code and tests while a verifier reviews the diff blind, and hooks block a commit until the full test suite passes.

App and UI Builders

Prompt-to-app and prompt-to-site builders, plus design-to-code and UI generators.

• a0.dev - An AI mobile app builder for iOS and Android applications.
• Anima - Converts Figma designs into React, HTML, and Vue code with AI, and offers a prompt-based builder for turning designs into working apps.
• AppWizzy - An AI web app builder with dedicated cloud development VMs, runtime templates, and Git-based source editing.
• Appypie - An AI-powered mobile app generator for creating iOS and Android applications without coding.
• Base44 - An AI coding tool for building full-stack web applications and MVPs with complex integrations.
• Bolt.diy - An open-source, self-hosted version of Bolt.new with support for multiple LLM providers (Groq, Anthropic, Ollama, etc.) for building full-stack applications.
• Bolt.new - A browser-based platform that uses AI and WebContainers technology to create, run, edit, and deploy full-stack web applications directly in the browser from natural language prompts.
• BoringUi - A JSON-based UI generator that produces HTML and Tailwind CSS output for creating user interfaces.
• Chef - Convex's AI app builder that generates full-stack web apps with a reactive database, authentication, and file storage built in.
• Clone UI - A tool dedicated to generating Tailwind CSS UI components.
• Codejet - A Figma to code conversion platform that transforms designs into production-ready frontend code.
• CodeParrot - A VS Code plugin that generates frontend code from Figma designs, aiming to reuse existing components and coding standards.
• CodePlatform - A mobile app development platform with AI capabilities.
• Co.dev - An AI-powered app development platform that helps build and deploy full-stack applications.
• Create.xyz - An AI tool focused on creating prototypes and website designs.
• Delta AI - An architecture-first backend generator that designs domains, service boundaries, and contracts from a product description, writes a spec for each service, and opens one pull request per service in your GitHub org.
• DemoGPT - An auto Gen-AI App Generator powered by Llama 2 for building applications.
• DESIGN:OS Studio - A source-available (PolyForm Shield) desktop design studio where Claude Code, Codex or Gemini CLI edit .fig files through 39 MCP tools and generate React, Tailwind or SwiftUI code.
• DiagramGPT - A free AI-based web app that converts schemas, infrastructure definitions, code snippets, or plain language into various diagrams.
• Dyad - A local, open-source AI app builder for creating full-stack applications with model choice, code export, Supabase integration, and MCP support.
• e2b_Fragments - A platform for building and deploying AI-powered applications with sandboxed environments.
• Emergent - An agentic platform that builds and deploys full-stack web and mobile apps from natural language prompts.
• Figma Make - Figma's prompt-to-app tool for turning designs and prompts into interactive, code-backed prototypes and web apps.
• Firebase Studio - Google's browser-based, agentic development environment for prototyping, building, and deploying full-stack AI apps with Gemini.
• Frontend AI - An AI tool focused on creating prototypes and website designs.
• Frontly - A web tool that converts uploaded images into HTML and CSS code.
• Galileo AI - A text-to-UI platform for generating user interfaces from text prompts (currently waitlisted).
• GitHub Spark - A platform for creating micro applications through natural language with instant deployment and AI integration.
• GitWit - A web-based editor for building ReactJS applications with AI assistance.
• Glowbom - A multi-platform app generator that uses AI to create applications for both mobile and web.
• GoCodeo - An AI agent for building full-stack apps in minutes with one-click Vercel deployment and seamless Supabase integration, featuring Model Context Protocol (MCP) support.
• Google AI Studio - Google's browser-based environment for prototyping Gemini-powered applications, prompts, multimodal workflows, and AI-generated app experiences.
• Google Stitch - Google's AI UI design tool that generates web and mobile interfaces from prompts or images and exports to Figma or front-end code.
• GPT Web App Generator - A full-stack app generator that creates React/Node.js/Prisma/Wasp applications from a short description.
• Hostinger Horizons - An AI app and website builder that turns prompts into hosted web apps with code editing, backend features, integrations, and one-click launch.
• Kombai - An AI tool for converting Figma designs into frontend code.
• Lazy AI - An AI coding tool for building full-stack web applications and MVPs with complex integrations.
• LlamaCoder - An open-source code generation model for building applications using Open Source LLMs.
• Locofy - Converts Figma and Penpot designs into production-ready front-end code for React, Next.js, React Native, Flutter, and HTML.
• Lovable.dev - An AI-powered platform for generating full-stack web applications from plain English descriptions, with shadcn/ui components and Supabase integration.
• Macaly - An AI platform that turns a prompt into a live website or web app, aimed at founders and small businesses.
• Mage - A full-stack web app generator that creates applications in Wasp, React, Node.js, and Prisma.
• Magic Patterns - A comprehensive UI prototyping tool with a Chrome extension and Figma plugin for generating UI from prompts, images, or design inspiration.
• Make Real - An online canvas that can be used to generate HTML/JavaScript applications.
• Marblism - A SaaS boilerplate generator that creates a full SaaS codebase from prompts.
• Massvai - An AI app builder whose coding agent turns a prompt into a full-stack Next.js + TypeScript app with live preview, Supabase auth/database setup, GitHub sync, and one-click Vercel deployment; the generated code is exportable.
• Memex - A desktop AI tool (for Mac, Linux, and Windows) that transforms natural language into working applications across any stack.
• Modaal - A Mac app that builds native iOS and Android apps in SwiftUI and Jetpack Compose with your own AI coding agent, starting from a PRD and a per-feature spec you approve.
• Newly - AI app builder for creating native iOS and Android apps from natural-language prompts.
• Onlook - An open-source visual editor for React and Tailwind apps where you design in the browser and AI writes the code.
• OpenMagic - An AI-powered coding toolbar for any web app that captures element context, previews diffs, and applies approved changes through a reverse proxy.
• OTF UI - MIT React components for web and React Native components for iOS and Android; agent skills for UI, native UI, tokens, and cross-platform UI install with npx skills add otf-kit/skills.
• Pico - An end-to-end micro app generator with instant deployment.
• Polymet - An AI-powered tool to create and iterate product designs and user interfaces, providing production-ready front-end code.
• Rapidpages - An open-source UI generator for rapid web interface creation.
• Readdy - An AI website builder that generates functional sites with a backend, templates, SEO tools, and hosting in one workflow.
• Rendition Create - A browser-based tool for creating and iterating new UI components.
• Rocket - An AI app builder that researches the market, recommends what to build, and generates production-ready code.
• Rork - An AI app builder that generates native mobile apps with React Native and Expo from natural language prompts.
• Same - An AI app builder that clones existing websites or builds new full-stack web apps from prompts.
• Second.dev - A platform for adding features to full-stack applications using AI.
• SoftGen AI - An AI-powered software generation platform for building web applications.
• Softr - An AI app generator with mobile support.
• Srcbook - A TypeScript-centric app development platform with an AI app builder and TypeScript notebook.
• Tempo - A WYSIWYG editor for React interfaces, likely leveraging AI for faster development.
• Trickle - An AI agentic canvas for vibe coding with built-in image and video generation, models, database, and design for building and launching apps and websites.
• Uizard - A multi-screen mockup generator and editor that creates designs from text prompts or by transforming screenshots/wireframes.
• v0.dev - Vercel's AI-powered tool for generating React components from text descriptions, using shadcn/ui components.
• Vibecode - An AI app builder that turns a described idea into a native iPhone, Android, or web app you can publish to the App Store.
• Visual Copilot - A Figma plugin for multi-framework code generation.
• Vitara - An AI-powered vibe coding platform for building, deploying, and scaling software products through a chat interface.
• vx.dev - A GitHub integration focused on UI generation with built-in support for shadcn, lucide, and nivo charts.
• Webdraw - An AI tool focused on creating prototypes and website designs.
• Wegic AI - An AI tool focused on creating prototypes and website designs.
• WeInc - An AI website and app builder that generates React + Vite + Tailwind sites from natural language prompts using WebContainers, with visual editing and custom domains.
• Wrapif AI - An AI tool focused on creating prototypes and website designs.

Code Review, Testing, Security and Docs

AI code review, test generation, QA, security scanning, documentation, debugging, and LLM observability.

• Adrenaline - A web-based AI-powered debugging assistant and chatbot that analyzes code, error messages, and stack traces to suggest fixes.
• AI Badger - A local-first tool with CLI and VS Code workflows for extracting focused repository context for ChatGPT, Claude, Gemini, Grok, and other AI assistants without requiring provider API integration.
• AI Kernel Explorer - A tool for understanding Linux kernel code with AI assistance.
• Aikido - A developer-focused security platform that combines SAST, dependency, secrets, IaC, and container scanning with AI-generated autofixes and noise reduction.
• Applitools - A visual AI testing platform that compares UI screenshots across environments, using AI to detect meaningful visual regressions.
• Arize Phoenix - An open-source LLM observability and evaluation tool for tracing, debugging, and testing AI applications, built on OpenTelemetry.
• Atomist - A platform that enables automatic code modification and refactoring through "code transformations."
• Autodoc - A tool for generating codebase documentation using large language models like OpenAI and Alpaca.
• Baz - An AI code review platform that analyzes pull requests with codebase context, flags breaking changes, and posts review comments.
• Betterloop - A script tag that watches real sessions for rage clicks, dead buttons, JavaScript errors and slow pages, and returns one ranked list of fixes that coding agents can read through MCP.
• Blinky Debugging Agent - A debugging agent for VS Code that helps identify and fix backend errors, inspired by SWE-agent.
• Braintrust - A platform for evaluating, logging, and monitoring LLM applications, with prompt playgrounds, datasets, and CI-friendly evals.
• Buildkite - A build automation platform with AI-enhanced pipeline optimization features.
• Callstack.ai Code Reviewer - An AI-powered PR reviewer for GitHub, designed to identify bugs, security issues, and performance bottlenecks.
• Checksum AI - An end-to-end autonomous QA automation agent that generates CI/CD ready Playwright tests directly to the repository.
• Codacy - An automated code quality and performance analysis platform that integrates with Git repositories.
• CodeAct - An AI-powered tool for advanced debugging, including multi-threading and concurrency analysis.
• CodeAnt AI - An AI tool that automatically creates pull requests to fix code issues.
• CodeCanary - An open-source AI code review tool for GitHub Actions or local use, offering incremental reviews, conversational re-evaluation, anti-hallucination safeguards, and multi-LLM support.
• CodeClimate - A platform that provides code quality and maintainability insights through automated analysis.
• CodeFlash AI - A CLI and CI tool that uses AI for optimizing Python code.
• CodeGate - An AI coding protection and encryption tool designed to maintain control and security when using AI coding assistants.
• CodeRabbit - An AI-powered code review platform that provides context-aware pull request reviews with intelligent feedback.
• Code Review GPT - An open-source tool for automated pull request reviews, available as a GitHub Action, GitLab CLI, or locally.
• Code to Flow - A tool to visualize, analyze, and understand code with interactive flowcharts generated by AI.
• Corgea - A GitHub integration that helps detect and fix security vulnerabilities in code.
• Critique - A GitHub-native AI code review agent that uses multiple specialist agents to assess pull request risks across security, architecture, performance, and correctness.
• cubic - An AI code review tool for GitHub pull requests that learns team conventions and posts inline comments with suggested fixes.
• Datadog - An application monitoring platform with AI-powered insights and observability features.
• DeepCode - An AI-based static analysis tool for finding bugs, security vulnerabilities, and offering refactoring suggestions.
• DeepSource - A code quality and security platform with static analysis, AI-powered autofixes, and code review for pull requests.
• DeepWiki - Cognition's AI-generated documentation for GitHub repositories, with architecture diagrams, a chat interface, and an MCP server.
• DevAssure - A code-aware autonomous testing agent that maps code changes to impacted tests and runs targeted validation from VS Code, Cursor, CLI, and CI workflows.
• DiffBlue Cover - An AI-powered tool that autonomously writes Java unit tests by analyzing code and generating comprehensive test coverage.
• DocuWriter.ai - An AI-powered web app for generating automated code and API documentation from source code files.
• Ellipsis - An AI code review bot that reviews pull requests, catches bugs, and can implement requested changes directly on GitHub.
• Explain Code - An AI-powered tool for code explanation and documentation, making complex code easier to understand.
• Functionize - An intelligent testing platform that uses AI/ML for creating, executing, and maintaining automated functional tests, particularly for web applications.
• GitHub Copilot Code Review - GitHub Copilot's AI-powered code review feature for pull requests and IDE workflows, providing contextual feedback and applicable suggestions.
• Goast - A hosted tool that ingests error logs and suggests fixes using AI.
• Graphite - A code review platform built around stacked pull requests, with an AI reviewer that posts feedback and suggested fixes.
• Harness - An AI-powered continuous delivery and deployment platform.
• Helicone - An open-source LLM observability platform and AI gateway for logging, monitoring, and debugging LLM requests.
• IMQA - An AI testing platform for creating natural-language tests with self-healing selectors, cross-browser execution, and video evidence capture.
• Keploy - An open-source API testing tool that records real traffic to generate test cases and data mocks automatically, with AI-assisted unit test generation.
• Kodus - Open-source, self-hosted AI code review that works on pull requests with your own LLM.
• Korbit - An AI code review tool that analyzes pull requests for bugs, security issues, and performance problems, with team insights.
• KushoAI - An AI agent for comprehensive API testing, transforming Postman collections, OpenAPI specs, and curl commands into exhaustive test suites.
• Langfuse - An open-source LLM engineering platform for tracing, prompt management, evaluations, and datasets.
• LangSmith - LangChain's platform for tracing, debugging, evaluating, and monitoring LLM applications and agents.
• Mabl - An intelligent test automation platform with self-healing tests, designed to reduce test flakiness and maintenance effort.
• Matter AI - An open-source AI Code Reviewer designed to help engineering teams release code with confidence.
• Meticulous.ai - A platform for automatically generated and maintained end-to-end tests that evolve as your application changes.
• Mintlify - An AI-powered documentation generation and maintenance platform for creating beautiful and functional documentation.
• Momentic - An AI testing platform that writes, runs, and self-heals end-to-end tests from natural-language steps.
• New Relic - A performance monitoring platform with intelligent alerting and AI-powered insights for application observability.
• Northflank - A platform for deploying and running applications and AI workloads, with support for isolated, ephemeral environments for executing code and agents.
• Nova - A CI bot that adds actions like summaries and tests to new pull requests.
• Ogoron - An AI testing platform that analyzes code changes and application architecture to generate and maintain API, UI, and mobile tests.
• OrcaCode Review - A GitHub Action that reviews each pull request against a P0-P3 severity rubric, posts findings inline on the affected lines, and fails the check on P0/P1 so it acts as a merge gate. The reviewing model, the rubric, and the merge policy are configured outside the workflow YAML.
• PitchDocs - A Claude Code plugin that generates professional, marketing-ready repository documentation — README, CHANGELOG, CONTRIBUTING, AI context files, and 15+ more files with evidence-based feature extraction and quality scoring.
• Pixee - Pixeebot automatically finds security and code quality issues, creating merge-ready pull requests with recommended fixes.
• PR-Agent - An open-source AI pull request reviewer, maintained by the community as the original Qodo project.
• PR Explainer Bot - A GitHub integration that adds explanatory comments to newly created pull requests.
• Promptfoo - An open-source CLI for testing and red-teaming LLM prompts, agents, and RAG pipelines, with CI integration.
• QA Wolf - An AI-assisted QA service that builds and maintains automated Playwright end-to-end test suites for web and mobile apps.
• Quack AI - A VS Code extension for adhering to project coding guidelines and enforcing standards.
• README-AI - An automated README.md file generator powered by large language model APIs.
• Semgrep - A static analysis platform for code, dependencies, and secrets, with an AI assistant that triages findings and suggests fixes.
• Sentry AI Autofix - A feature of the Sentry error tracking platform that uses AI to analyze production errors and suggest code patches.
• Snyk - A developer security platform that helps find and fix vulnerabilities in code, dependencies, and containers.
• Snyk Code - A SAST (Static Application Security Testing) tool that uses symbolic AI to find security vulnerabilities and quality issues with high precision.
• SonarQube - A leading platform for continuous code quality and security analysis, with evolving AI-enhanced features.
• Sourcery - An AI code reviewer and linter that suggests bug detection and quality improvements across over 30 languages.
• Stenography.dev - An AI-powered tool for generating code documentation.
• Supacodes - An AI tool for automating GitHub code documentation.
• Swimm - An AI assistant for contextual code understanding, using static analysis and AI-generated documentation.
• Test Gru - Provides enterprise-level unit test automation services.
• Testim - An AI-based test automation platform for creating stable end-to-end tests for web applications, with AI to improve locators and reduce maintenance.
• Traceloop - A tool that uses OpenTelemetry tracing data with generative AI to improve system reliability.
• Trelent - A VS Code extension for generating docstrings using proprietary AI models.
• Tusk - An AI test generation tool that writes unit and integration tests for pull requests and catches edge cases before merge.
• What The Diff - An AI-powered app that reviews pull request diffs and writes descriptive comments about the changes in plain English.
• ZeroPath - An AI-native application security scanner that finds logic flaws, auth issues, and vulnerabilities, and generates patches.

Other Developer Utilities

SQL and database assistants, shell and Git helpers, agent-building frameworks, project management, and local model tools.

• AI2SQL - An AI-powered SQL query builder that converts natural language descriptions into SQL queries and offers optimization.
• AI Code Convert - A web-based tool for translating code between programming languages using AI.
• AI Code Playground - A web-based tool for refactoring and improving code quality with AI assistance.
• AutoRegex - A web tool that uses OpenAI's GPT-3 to produce regular expressions from plain English descriptions.
• Butterfish - A CLI tool that embeds ChatGPT directly into your shell for easy access and simple agentic capabilities.
• ChatWithGit - A ChatGPT plugin that enables searching GitHub repositories and returning relevant links.
• Composio - An open-source toolset designed for building and managing AI Agents and LLMs.
• CrewAI - A platform and framework for building, deploying, and managing multi-agent workflows with no-code tools, CLI support, and code-first APIs.
• database.build - An in-browser Postgres sandbox from Supabase where an AI assistant designs schemas, writes SQL, and generates migrations.
• GitBrain - A Git client that uses AI to simplify the Git workflow by splitting code changes, generating summaries, and writing commit messages.
• GitButler - A Git client that allows for simultaneous branches on top of existing workflows, with AI assistance for generating conventional commit messages.
• GitFluence - A web-based tool that uses AI to automatically generate Git commands from text descriptions.
• gptcomet - An AI-powered CLI tool for generating commit messages and reviewing changes.
• GPT Migrate - A CLI agent that can convert a full-stack application from one language or framework to another using GPT-4 with a large context window.
• Height - An intelligent project management tool with AI-powered features for automated task organization and issue tracking.
• LangGraph - LangChain's low-level orchestration framework and runtime for building reliable, controllable AI agents and agent workflows.
• Linear - A project management tool with AI-powered features for issue tracking and automated task organization.
• LM Studio - A desktop app for discovering and running local LLMs, with an OpenAI-compatible local server that coding agents can use.
• Microsoft AutoGen - A framework and Studio UI for building, prototyping, and orchestrating single-agent and multi-agent AI applications.
• OneCompiler - A free AI-powered online compiler supporting over 70 languages for writing, running, and sharing code.
• Potpie - An open-source platform for creating AI Agents for your codebase in minutes, with pre-built agents for Q&A, Testing, Debugging, and System Design.
• Shell GPT - A command-line productivity tool that uses LLMs to generate shell commands, code snippets, and answers from the terminal.
• Shell Whiz - A highly configurable CLI assistant for generating and explaining shell commands.
• SQLAI.ai - An AI tool for SQL query generation, optimization, and explanation, with the ability to train on database schemas.
• SuperAGI - An open-source platform for building and managing LLM-based agents.
• TEXT2SQL.AI - An AI tool for SQL query translation and explanation.
• TinyTools - A collection of free browser-based developer utilities including an AI Cost Calculator for comparing LLM pricing, an AI Robots.txt Generator for LLM crawlers, an AI Content Disclosure Generator (EU AI Act Article 50 compliant), an AI Background Remover that runs locally via WebAssembly, plus OG image, favicon, color palette, and SEO meta tag generators. No signup, open source.
• WhoDB - An AI-powered data explorer for various databases.
• Wren AI - An open-source SQL AI Agent that allows users to get results and insights by asking questions without writing SQL.

---

Contributing

Contributions are welcome. Please read the contributing guidelines before opening a pull request. In short:

• Put the tool in the section that fits it, in alphabetical order, using the existing format: **[Tool Name](https://example.com/)** - Brief description.
• Keep descriptions concise, neutral, and focused on concrete developer-facing capabilities.
• Include an official website, documentation page, or public repository link.
• Avoid duplicate entries, generic AI products without a clear developer use case, and purely promotional language.
• Open an issue or pull request with enough context to explain why the tool belongs in this list.

License

This project is shared as a curated community resource. Please check the repository for license details before reusing the content.

---

Last updated: November 2026