It's not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. It's an autonomous agent that lives on your server, remembers what it learns, and gets more capable the longer it runs.
Works on Linux, macOS & WSL2 · No prerequisites · Installs everything automatically
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bashInstalls uv, Python 3.11, clones the repo, sets up everything. No sudo needed.
# Interactive setup wizard
hermes setup
# Or choose your model
hermes modelConnect to Nous Portal (OAuth), OpenRouter (API key), or your own endpoint.
hermesThat's it. Full interactive CLI with tools, memory, and skills.
# Interactive gateway setup wizard
hermes gateway setup
# Start the messaging gateway
hermes gateway
# Install as a system service
hermes gateway installWalk through connecting Telegram, Discord, Slack, or WhatsApp. Runs as a systemd service.
hermes updatePulls the latest changes and reinstalls dependencies. Run anytime to get new features and fixes.
Native Windows support is extremely experimental and unsupported. Please install WSL2 and run Hermes Agent from there.
Telegram, Discord, Slack, WhatsApp, and CLI from a single gateway — start on one, pick up on another.
Persistent memory and auto-generated skills — it learns your projects and never forgets how it solved a problem.
Natural language cron scheduling for reports, backups, and briefings — running unattended through the gateway.
Isolated subagents with their own conversations, terminals, and Python RPC scripts for zero-context-cost pipelines.
Five backends — local, Docker, SSH, Singularity, Modal — with container hardening and namespace isolation.
Web search, browser automation, vision, image generation, text-to-speech, and multi-model reasoning.
40+ built-in — web search, terminal, file system, browser automation, vision, image generation, text-to-speech, code execution, subagent delegation, memory, task planning, cron scheduling, multi-model reasoning, and more.
Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI — all from a single gateway. Connect to Nous Portal, OpenRouter, or any OpenAI-compatible API.
Run locally, in Docker, over SSH, on Modal, Daytona, or Singularity. Container hardening with read-only root, dropped capabilities, and namespace isolation.
40+ bundled skills covering MLOps, GitHub workflows, research, and more. The agent creates new skills on the fly and shares them via the open agentskills.io format. Install community skills from ClawHub, LobeHub, and GitHub.
Batch trajectory generation with parallel workers and checkpointing. Atropos integration for RL training. Export to ShareGPT for fine-tuning with trajectory compression.