Vibe Coding Discoveromega-memory
View on GitHubPersistent memory for AI coding agents
OMEGA is a local-first persistent memory system for AI agents, exposed as an MCP server and Python library. It stores memories in SQLite and uses on-device embeddings for semantic recall across coding sessions and supported clients.
Use Cases
Persist coding decisions and preferences across agent sessionsRetrieve relevant project context with semantic searchCapture lessons from errors to help prevent repeated mistakesResume work using saved task checkpointsShare memory across different AI models and coding clients
Built With
- Language
- Python
- Frameworks
- Model Context Protocol · ONNX Runtime · SQLite-vec
Tags
persistent memory · AI agents · coding agents · MCP server · local-first · semantic search · knowledge graph · cross-session context · Claude Code · Cursor