Mem0 is an open-source memory layer for AI assistants and agents, offering persistent personalized memory via Python/TS SDKs, CLI, self-hosted server, or cloud. Supports multi-level memory, hybrid retrieval, temporal reasoning, and many LLM providers.
Open source. Open possibilities.
Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONPersistent memory engine for AI coding agents. Auto-captures sessions via hooks, stores in SQLite with BM25/vector/graph hybrid search, and serves 54 MCP tools across 20+ agents. Self-hosted, keyless, zero external dependencies.
Lemory is a local middleware that transforms markdown notes (e.g., Obsidian vaults) into a context database for AI agents. It supports keyless on-device hybrid search, Korean-specific processing, hierarchical token savings, and knowledge graph visualization, integrating with various AI tools via MCP.
MCP Context Server is a FastMCP-based server providing persistent multimodal context storage for LLM agents, featuring full-text, semantic, and hybrid search with cross-encoder reranking, thread-based scoping, and support for SQLite and PostgreSQL backends.
Supermemory is an open-source memory and context engine for AI, offering persistent memory across conversations, user profiles, hybrid search, connectors, and local self-hosting. It claims top benchmarks in AI memory performance.