omega-memory/omega-memory

**Cross-model memory for AI agents. Local-first. Works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client.** Your agent's brain shouldn't live on someone else's server, or be locked to one provider.
---
The Problem
AI coding agents are stateless. Every new session starts from zero. The "solutions" either lock you into one model provider or send your codebase context to their cloud.
- **Context loss.** Agents forget every decision, preference, and architectural choice between sessions. Developers spend 10-30 minutes per session re-explaining context that was already established.
- **Repeated mistakes.** Without learning from past sessions, agents make the same errors over and over. They don't remember what worked, what failed, or why a particular approach was chosen.
- **Cloud memory = someone else's database.** Services like Mem0 require API keys and send your data to their servers. When they change pricing, get acquired, or go down, your agent's accumulated intelligence disappears.
- **Vendor lock-in.** Anthropic's Memory Tool only works with Claude. OpenAI's memory only works with GPT. Switch models, lose your memory.
OMEGA solves this. Memory, coordination, and learning that runs entirely on your machine. Works with every major LLM and coding agent. No cloud. No API keys. No vendor lock-in.
Quick Install
OMEGA needs **Python 3.11 or newer**. Check with python3 --version: macOS ships Python 3.9, which is too old. If pip answers No matching distribution found for omega-memory, that is the reason; install a newer Python first (for example brew install python@3.12, or from python.org).
Install OMEGA into its own environment. Homebrew's Python refuses a plain pip install (PEP 668), and an isolated install keeps OMEGA's dependencies away from your projects. Pick one:
Keep the quotes around "omega-memory[server]": zsh, the default macOS shell, treats bare square brackets as a pattern and fails. The [server] extra installs the MCP server, which also runs the hook daemon; without it Claude Code gets no OMEGA tools and no hooks.
Then:
omega setup --dry-run shows what setup would change without writing or downloading anything.
Claude Desktop
This registers OMEGA as an MCP server in Claude Desktop's config. Restart Claude Desktop to activate.
Cursor, Windsurf, Cline, Codex, Antigravity
Codex and Antigravity get their config file written; for the others setup prints the JSON block to paste. For any other MCP client, omega setup --client venv prints the command and arguments to use. Hooks (automatic capture and surfacing) are available with Claude Code only.
Library-only install (no MCP server)
If you only need OMEGA as a Python library for scripts, CI/CD, or automation, install it into your project's environment:
This gives you the full storage and retrieval API without running an MCP server. Hooks need the MCP server (the hook daemon runs inside it), so a library-only install has no automatic capture or surfacing.
From Source
omega setup will:
1. Create ~/.omega/ (or $OMEGA_HOME if you set it)
2. Download the ONNX embedding model, bge-small-en-v1.5 (~130 MB), and a reranker (~90 MB) to ~/.cache/omega/models/
3. Register omega-memory as an MCP server (Claude Code auto-detected, or specify --client)
4. Install session hooks into ~/.claude/settings.json
5. Add an OMEGA block to ~/.claude/CLAUDE.md
If a step fails, the summary marks it [FAIL] with the reason and setup exits with an error.
60-Second Quickstart
OMEGA works through natural language — no API calls, no configuration. Just talk to Claude.
**1. Tell Claude to remember something:**
> "Remember that the auth system uses JWT tokens, not session cookies"
Claude stores this as a permanent memory with semantic embeddings.
**2. Close the session. Open a new one.**
**3. Ask about it:**
> "What did I decide about authentication?"
OMEGA surfaces the relevant memory automatically: