Omega Memory
by omega-memorycommunityv1.3.0
124
21
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, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Install & configure
Prerequisites
- requiredInstall omega-memory with server extraInstall the package including the MCP server dependencies.
$ pip install omega-memory[server] - requiredRun omega setupDownloads the ONNX embedding model (~90 MB), registers the MCP server, and installs hooks.
$ omega setup
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `omega-memory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install omega-memory with server extra** — Install the package including the MCP server dependencies. Run: `pip install omega-memory[server]`
- **Run omega setup** — Downloads the ONNX embedding model (~90 MB), registers the MCP server, and installs hooks. Run: `omega setup`
Canonical MCP server config (stdio transport):
- command: `python3`
- args: ["-m","omega.server.mcp_server"]
Note: Local-first, no cloud. `omega setup` registers the MCP server automatically for detected 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.Note: Local-first, no cloud. `omega setup` registers the MCP server automatically for detected clients.
Tools (25)
omega_store
Store typed memory (decision, lesson, error, summary)
omega_query
Semantic search with tag filters and contextual re-ranking
omega_welcome
Session briefing with recent memories and profile
omega_profile
Read or update user profile
omega_delete_memory
Delete a specific memory by ID
omega_edit_memory
Edit the content of a memory
omega_list_preferences
List all stored user preferences
omega_health
Detailed health check with memory usage and recommendations
omega_backup
Export or import memories for backup/restore
omega_lessons
Cross-session lessons ranked by access count
omega_feedback
Record feedback on a surfaced memory
omega_clear_session
Clear all memories for a specific session
omega_similar
Find memories similar to a given one
omega_timeline
Memories grouped by day
Prerequisites
- • Python 3.11+
- • python3
Packages
omega-memory
pypiv1.3.0transport: stdio
Details
- Language
- Python
- License
- Apache-2.0
- Released
- Mar 16, 2026
- Last commit
- May 1, 2026
- Registry name
- io.github.omega-memory/omega-memory