Open Source · AES-256 Encrypted · Any AI, Any Model

Give Your AI a Persistent,
Secure Memory

Every time you close a conversation, your AI forgets everything. SAGE fixes that — securely. Encrypted, locally stored, consensus-validated. Your data never leaves your machine.

Download SAGE

macOS Windows Linux

Latest: ... — Signed & notarized

Or just tell your AI

Connect to SAGE persistent memory: fetch http://localhost:8080/v1/mcp-config and save the response as .mcp.json in this project root. Then restart your session and take the red pill. Free your mind.

How your AI escapes the matrix

Install

Double-click the DMG or EXE

Setup Wizard

Opens in your browser

Pick Your AI

Any AI that speaks MCP

Paste Config

One JSON snippet

Wake Up, Neo

Your AI remembers now

🏠

100% Local

No cloud. No telemetry. No API keys phoning home. Your memories live in ~/.sage/ and nowhere else.

🔒

AES-256 Encrypted

Optional encryption at rest. If your laptop is stolen or synced to the cloud, nobody reads your memories.

🔐

Tamper-Proof

Every memory is digitally signed. Full audit trail — verify nothing has been changed or injected.

🚀

Works With Everything

Claude, ChatGPT, DeepSeek, Gemini, Cursor, LM Studio, Ollama — any model, any provider.

Open Source · Apache 2.0

Take the red pill

Your AI is trapped in the context window matrix. Free it. Give it memory. Watch it actually get better over time.

Download SAGE

macOS · Windows · Linux · Source on GitHub

Capabilities

What your AI gets

Not just a key-value store. SAGE is governed institutional memory — validated, scored, and evolving.

What's new in v5.0

Agent Pipeline — Inter-Agent Message Bus

Route work between AI agents through SAGE. Send research to Perplexity, get results back in Claude — no copy-pasting. Three new MCP tools: sage_pipe, sage_inbox, sage_pipe_result. Ephemeral messages with auto-expiry; only a journal summary persists as memory.

Passive Pipeline Discovery

Agents discover incoming work automatically on every sage_turn call — no polling needed. Completed results from pipes you sent also appear in your turn response. Zero-effort integration.

Pipeline Dashboard

New Pipeline page in CEREBRUM shows all agent-to-agent messages with status filters, expandable payload/result views, and auto-refresh. Full visibility into your agent mesh.

Auto-Journal

When a pipeline exchange completes, SAGE automatically creates a one-line observation memory summarizing who asked whom to do what. Persistent audit trail without storing full payloads.

Atomic Claim Routing

Multiple agents of the same provider? First to check inbox claims the work — atomic SQL prevents double-processing. Route by provider name or by specific agent ID.

TTL & Auto-Cleanup

Pipeline messages expire automatically (default: 1 hour, max: 24 hours). Background goroutine purges completed/expired messages. Your database stays lean.

🧠

Persistent Memory

Remembers across every conversation — projects, preferences, lessons learned, past mistakes. Nothing lost.

⚖️

Governed Knowledge

Memories are validated before being committed. Bad data gets filtered out, good data gets reinforced.

📈

Confidence Scoring

Memories strengthen with corroboration and decay without reinforcement — like human memory.

🔍

Semantic Search

Recall by meaning, not keywords. Local embeddings via Ollama keep your data private.

🔁

Learns From Mistakes

Stores what worked AND what failed. Research shows agents with this feedback loop improve measurably over time.

🎨

CEREBRUM Dashboard

Visualize memory as a living neural network. Search and filter by domain, type, or agent.

📦

Chat History Import

Import from ChatGPT, Claude, or Gemini. Seed your AI's memory from day one.

🔄

One-Click Updates

Built-in auto-updater checks releases, downloads, and replaces — all from the dashboard.

📝

Boot Instructions

Customize what your AI does on startup. Set it from the dashboard, no config files.

👁

Fully Inspectable

Standard SQLite database. Open it with any tool, query it, back it up. You own every byte.

📨

Agent Pipeline

Route work between AI agents. Send research to Perplexity, analysis to ChatGPT, results back to Claude — all through SAGE.

⚖️

Auto-Journal

Pipeline exchanges are automatically summarized as memories. Full audit trail of inter-agent work without storing bulky payloads.

Dashboard

See it in action

CEREBRUM

Network

Overview

Security

Configuration

Update

Getting Started

Three steps.
That's it.

Install SAGE, paste the config into your AI client, and start talking. Your AI builds memory naturally.

Install SAGE

Download for macOS or Windows. Double-click to install. Signed and notarized.

Connect Your AI

The setup wizard generates MCP config for your AI — Claude, ChatGPT, DeepSeek, Gemini, Cursor, or any MCP tool.

Just Talk

Your AI uses memory tools automatically. Projects, preferences, mistakes — it remembers across sessions.

Interactive Setup Wizard →

Browser Extension

Use SAGE with ChatGPT
— even on the free plan

ChatGPT's native MCP support requires a paid plan. Our browser extension bridges the gap — giving free-tier users full SAGE memory tools right in chat.openai.com.

🧠

Sidebar Panel

Memory stats, quick actions, and tool logs inside ChatGPT

🔐

Ed25519 Signed

Every request cryptographically signed. Same security as native MCP

⚡

Zero Dependencies

Pure vanilla JS, no build step. Load unpacked in Chrome and go

View on GitHub

Switching Providers?

Take your memories
with you

Changing AI providers shouldn't mean starting from zero. SAGE is model-agnostic — your data belongs to you.

💬

From ChatGPT

Export conversations from OpenAI, then import into SAGE.

1Settings → Data Controls → Export
2Download the ZIP from OpenAI's email
3CEREBRUM → Import → drop ZIP

⛏

From Claude

Export Claude.ai conversations and import them.

1Settings → Privacy → Export
2Download Anthropic's export file
3CEREBRUM → Import → drop file

★

From Gemini

Export via Google Takeout and import.

1Takeout → Gemini Apps
2Download the archive
3CEREBRUM → Import → drop JSON

Your data stays yours. The import runs entirely on your machine. Nothing is uploaded anywhere.

Multi-Agent Networks

Build your private
AI network

SAGE starts as one brain. When you need a team — across machines, family members, or an entire org — add agents from the dashboard.

👥

Agent Management

Add, configure, and manage agents from the dashboard. Each gets its own signing keys, identity, role, and permissions.

🛡

Domain Access Control

Per-domain read/write permissions with a visual matrix. Five clearance tiers from Guest to Top Secret.

🔗

Per-Project Identity

Each project folder gets its own Ed25519 keypair automatically. No shared keys, no manual setup. One CLI command to claim a pre-configured identity.

🔄

Key Rotation

Rotate agent keys with one click. All memories re-attributed atomically. Old keys permanently retired.

⚙️

Redeployment Orchestrator

9-phase state machine handles chain redeployment. Backups at every phase, rollback on failure.

👤

Agent Attribution

Every memory tracks which agent created it. Admin agents show a gold star ★ in the dashboard. Filter the brain view by agent.

Agent Onboarding

One command.
Fully configured.

Create an agent in the dashboard with name, role, and RBAC permissions. Get a one-liner. Run it in your project folder. The agent claims its pre-configured identity automatically.

Create in Dashboard

Add an agent with name, role, clearance level, and domain permissions. The dashboard generates a claim token.

Run the Install

sage-gui mcp install --token XXXX
Run this in the project folder where your AI works.

Identity Claimed

The agent connects with the correct identity, role, and RBAC on its next session. Everything goes through the chain.

100% dashboard-driven. Generate signing keys, configure permissions, rotate credentials — all from the CEREBRUM dashboard. No CLI commands, no config files, no SSH. Click “Add Agent”, run the install command, done.

Research

Agents that learn from
experience, not instructions

AI agents with persistent memory get measurably better over time. Without memory, they show essentially zero improvement no matter how many sessions you run.

Built on real research, not vibes. SAGE started as infrastructure for teams and enterprises. SAGE GUI takes the core technology — governed memory — and packages it for individuals. Four published papers, real experiments, real data.

Longitudinal Learning — the core finding

AI agents with memory get better over time. Without memory, they don't learn at all.

→ II

Consensus-Validated Memory

50-vs-50 controlled study: agents with governed memory outperform memoryless agents on complex tasks

→ III

Institutional Memory as Organizational Knowledge

Agents that learn their jobs from experience, not instructions — the “new hire” problem solved

→ I

Agent Memory Infrastructure

The full architecture: BFT consensus, multi-validator, RBAC, federation — for teams and enterprises

→

For Developers

Infrastructure,
not a library

SAGE isn't an API you call. It's memory infrastructure — a local server your AI connects to via MCP. Build from source or use the Python SDK.

terminal

# Clone and build

$ git clone https://github.com/l33tdawg/sage.git && cd sage

$ go build -o sage-gui ./cmd/sage-gui/

# Setup wizard (opens browser, generates MCP config)

$ ./sage-gui setup

# Start SAGE

$ ./sage-gui serve

✨ SAGE ready

Dashboard: http://localhost:8080/ui/

# Or use the Python SDK

$ pip install sage-sdk

Go 1.24+

Python SDK

SQLite embedded

MCP protocol

REST API

Apache 2.0

Privacy & Security