Universal memory layer for AI Agents
Adding a persistent memory layer to agents across sessions and users.
You only need simple conversation history in a single session.
About mem0 #
All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops).
What changed: - Single-pass ADD-only extraction -- one LLM call, no UPDATE/DELETE. Memories accumulate; nothing is overwritten. - Agent-generated facts are first-class -- when an agent confirms an action, that information is now stored with equal weight. - Entity linking -- entities are extracted, embedded, and linked across memories for retrieval boosting. - Multi-signal retrieval -- semantic, BM25 keyword, and entity matching scored in parallel and fused. - Temporal Reasoning -- time-aware…
See the migration guide for upgrade instructions. The evaluation framework is open-sourced so anyone can reproduce the numbers.
mem0 is an open-source project written primarily in Python, with 61k stars on GitHub. It was last updated in July 2026.
npm install -g @mem0/cli # or: pip install mem0-cli