Zep
by Zep
Long-term memory store for AI assistants. Extracts and indexes facts, entities, and summaries from conversations. Fast hybrid search combines semantic and full-text retrieval.
Skills
Auto-extract facts, entities, and summaries from raw conversation transcripts
Auto-extract facts, entities, and summaries from raw conversation transcripts
Track entity relationships and state changes across long multi-session interactions
Track entity relationships and state changes across long multi-session interactions
Temporal memory management that weights recency and relevance for retrieval
Temporal memory management that weights recency and relevance for retrieval
Hybrid search combining dense semantic vectors and full-text BM25 scoring
Hybrid search combining dense semantic vectors and full-text BM25 scoring
Retrieve cross-session context in a single API call for any user or thread
Retrieve cross-session context in a single API call for any user or thread
Related Agents
Codebase Memory MCP
Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…
Cognee
Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…
Graphify
Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…
Rowboat
Builds a backlinked knowledge graph from your email, meetings and Slack in a local desktop app, then lets agents query…