mem0 shipped an update

Mem0, an open-source universal memory layer for AI agents, shipped an update introducing single-pass ADD-only extraction, agent-generated facts as first-class data, entity linking, multi-signal retrieval, and temporal reasoning. The project, written primarily in Python with 61k GitHub stars, last updated in July 2026, now includes an open-sourced evaluation framework for reproducibility.

mem0 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 mem0 vs. the alternatives All 22 alternatives → /alternatives/mem0