01AI-powered semantic search across all memories using embeddings
02Cross-session memory persistence across different AI agent conversations
03Unified memory layer accessible by any connected LLM (Claude, Qwen, Gemini, etc.)
04Comprehensive suite of 19 Model Context Protocol (MCP) tools for memory, logging, and workflow
05Docker-ready deployment with custom SQLite connection pooling and WAL mode for performance
06162 GitHub stars