Omega

v1.3.0Knowledge & Memorystable

🐍 🏠 🍎 🪟 🐧 - Persistent memory for AI coding agents with semantic search, auto-capture, cross-session learning, and intelligent forgetting. 12 MCP tools, local-first.

ai-agentai-memoryclaudeclaude-codecoding-agent
Share:
145
Stars
0
Downloads
0
Weekly
0/5

What is Omega?

Omega is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 🏠 🍎 🪟 🐧 - persistent memory for ai coding agents with semantic search, auto-capture, cross-session learning, and intelligent forgetting. 12 mcp tools, local-first.

🐍 🏠 🍎 🪟 🐧 - Persistent memory for AI coding agents with semantic search, auto-capture, cross-session learning, and intelligent forgetting. 12 MCP tools, local-first.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐍 🏠 🍎 🪟 🐧 - Persistent memory for AI coding agents with sema

Use Cases

Semantic search across agent memories
Auto-capture and intelligent forgetting
Cross-session learning for AI agents
omega-memory

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.3.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

PIP

pip install omega-memory

Manual Installation

pip install omega-memory

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Omega

Omega is a local-first persistent memory system for AI coding agents that gives them the ability to store, search, and retrieve knowledge across sessions using semantic similarity. It installs as a Python package and registers itself as an MCP server plus optional Claude Code hooks, exposing over 25 memory tools covering storage, retrieval, session management, analytics, reminders, and knowledge-graph traversal. Unlike in-context memory that resets each session, Omega maintains a SQLite database and ONNX embedding model locally so that agents can learn from past decisions, avoid repeating mistakes, and carry project context forward indefinitely.

Prerequisites

  • Python 3.9 or later with pip available
  • An MCP-compatible client: Claude Desktop, Claude Code, Cursor, Windsurf, Cline, or Codex
  • Approximately 100 MB of disk space for the ONNX embedding model cached at ~/.cache/omega/models/
  • No external API keys required — all embedding and storage runs locally
1

Install Omega with the MCP server extras

Install omega-memory with the server extra to get the MCP server entrypoint alongside the core library.

pip install omega-memory[server]
2

Run the setup wizard

Run omega setup to initialise the local database, download the ONNX embedding model, and register the MCP server with your chosen client.

omega setup
3

Set up for a specific client

Target a specific editor client. The setup wizard writes the MCP config and optional hooks automatically.

# For Claude Desktop
omega setup --client claude-desktop

# For Cursor
omega setup --client cursor

# For Claude Code
omega setup --client claude-code
4

Verify the installation

Run the built-in doctor command to confirm the database, embedding model, and MCP registration are all working correctly.

omega doctor
5

Restart your MCP client

Restart Claude Desktop or your editor. Omega's memory tools (omega_store, omega_query, omega_welcome, etc.) will appear in the available tools list.

Omega Examples

Client configuration

Manual claude_desktop_config.json entry if you prefer not to use the omega setup wizard.

{
  "mcpServers": {
    "omega": {
      "command": "python",
      "args": ["-m", "omega.server"]
    }
  }
}

Prompts to try

Example prompts that use Omega's memory tools for cross-session knowledge management.

- "Remember that this project uses JWT for auth, not session cookies — store this as a decision memory"
- "What architectural decisions have I made for the payments service?"
- "Store a lesson: always run database migrations in a transaction to allow rollback on failure"
- "What errors did I run into last week while working on the API gateway?"
- "Show me a weekly digest of what I've been working on and what I've learned"

Troubleshooting Omega

omega doctor reports embedding model not found

The ONNX model is downloaded on first setup. Run omega setup again to trigger the download, or manually verify that ~/.cache/omega/models/ exists and has write permissions.

MCP tools do not appear in Claude Desktop after setup

Confirm omega setup --client claude-desktop completed without errors, then fully quit and relaunch Claude Desktop (not just close the window). Check that ~/.claude/settings.json contains the omega MCP entry.

Memory queries return unrelated results

Semantic search quality improves as more memories are stored. Use omega_type_stats to see memory distribution and omega_consolidate to merge fragmented or duplicate memories that may be diluting search relevance.

Frequently Asked Questions about Omega

What is Omega?

Omega is a Model Context Protocol (MCP) server that 🐍 🏠 🍎 🪟 🐧 - persistent memory for ai coding agents with semantic search, auto-capture, cross-session learning, and intelligent forgetting. 12 mcp tools, local-first. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Omega?

Install via pip with: pip install omega-memory. Then configure your AI client to connect to this MCP server.

Which AI clients work with Omega?

Omega works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Omega free to use?

Yes, Omega is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "omega": { "command": "pip", "args": ["install", "omega-memory"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Omega?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides