# OMEGA Memory

Local cross-model storage that preserves project decisions, patterns, and context across agent sessions without sending data to cloud services.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 224
- Author: omega-memory
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/omega-memory/omega-memory
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/mcp/omega-memory

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add omega-memory -- uvx omega-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>

### Codex

**Platform CLI**
```bash
codex mcp add omega-memory -- uvx omega-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add omega-memory uvx omega-memory
```
uvx runs the command named after the package; if the README names another one, use uvx --from omega-memory <command>

## When to use it
- 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
- 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

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md