OMEGA Memory — Claude Code MCP server: what it does, how to install
Local cross-model storage that preserves project decisions, patterns, and context across agent sessions without sending data to cloud services.
claude mcp add omega-memory -- uvx omega-memoryWhat OMEGA Memory does
Most AI coding assistants reset after each session. Because of this, developers spend time repeating architectural details and preferences. OMEGA keeps track of past choices, mistakes, and project conventions on your local drive. Your project context never leaves your machine.
The system runs semantic search to surface past insights during subsequent prompts. Initial setup handles model downloads directly to your local cache. While the core MCP tools integrate with editors like Cursor and Windsurf, session hooks run exclusively inside Claude Code.
Running the server requires Python 3.11 or newer, meaning the default Python 3.9 on macOS fails to install the package. Setting up an isolated environment with uv or pipx avoids conflicts with existing dependencies.
What it helps with
- retain architectural decisions across separate coding sessions
- prevent repeated coding errors by recalling past outcomes
- store assistant memories locally without third-party databases
- switch between different coding models while keeping memory history
Example prompts for the agent
- Remember that we use strict TypeScript checks across all packages
- What approach did we pick for user authentication?
- Check past notes on why we chose JWT instead of cookies
How to install OMEGA Memory
Platform CLI
claude mcp add omega-memory -- uvx omega-memoryuvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>
Platform CLI
codex mcp add omega-memory -- uvx omega-memoryuvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>
Config file
{
"mcpServers": {
"omega-memory": {
"command": "uvx",
"args": [
"omega-memory"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>
Config file
{
"servers": {
"omega-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"omega-memory"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>
Platform CLI
gemini mcp add omega-memory uvx omega-memoryuvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about OMEGA Memory
How do I install OMEGA Memory in Claude Code?
Run claude mcp add omega-memory -- uvx omega-memory in your terminal.
What does OMEGA Memory do?
It stores development choices, project guidelines, and lessons in a local database so coding assistants recall past context automatically.
What Python version is needed for OMEGA Memory?
You need Python 3.11 or newer. The default Python 3.9 included with macOS will trigger an installation error.
