OMEGA is a local-first memory system for AI agents that allows them to retain context and learning across sessions without relying on cloud services or API keys. It supports multiple AI models and coding agents.
From the registry: Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.
$ pip install omega-memory[server]https://pypi.org/project/omega-memory/$ omega setupPlease install the `core-omegamemory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install OMEGA** — Install the omega-memory Python package with the server extra. Run: `pip install omega-memory[server]` (https://pypi.org/project/omega-memory/)
- **Run omega setup** — Downloads ONNX embedding model (~90MB), registers MCP server, installs hooks. Run: `omega setup`
Canonical MCP server config (stdio transport):
- command: `python3`
- args: ["-m","omega.server.mcp_server"]
Note: Local-first memory server. `omega setup --client <claude-desktop|cursor|claw-code|windsurf|cline|codex>` auto-registers with common clients.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI Agents Framework with Self Reflection and MCP support