mem0ai /mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
★ 69,014⑂ 8,215👁 252⑃ 5,168● 2,384▤ 416
+54
日增长
+337
周增长
69,014
stars
8,215
forks
252
watchers
5,168
prs
2,384
issues
416
releases
README
🎃 Register here → · Contributors get priority
Learn more
·
Join Discord
·
Demo
📄 Benchmarking Mem0's token-efficient memory algorithm →
New Memory Algorithm (April 2026)
| Benchmark | Old | New | Tokens | Latency p50 |
| --- | --- | --- | --- | --- |
| LoCoMo | 71.4 | 92.5 | 7.0K | 0.88s |
| LongMemEval | 67.8 | 94.4 | 6.8K | 1.09s |
| BEAM (1M) | — | 64.1 | 6.7K | 1.00s |
| BEAM (10M) | — | 48.6 | 6.9K | 1.05s |
All benchmarks run on the same production-representative model stack. Single-pass retrieval (one call, no agentic loops) at a top_200 retrieval budget. Scores reflect Mem0's managed platform, which includes proprietary optimizations not available in the open-source SDK; open-source users should expect directionally similar gains but not identical numbers.
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 retrieval that ranks the right dated instance for queries about current state, past events, and upcoming plans.
See the migration guide for upgrade instructions. The evaluation framework is open-sourced so anyone can reproduce the numbers.
Research Highlights
- 92.5 on LoCoMo -- +21 points over the previous algorithm
- 94.4 on LongMemEval -- +27 points, with 98.2 on assistant memory recall
- 64.1 on BEAM (1M) -- production-scale memory evaluation at 1M tokens
- Read the full paper
Introduction
Mem0 ("mem-zero") enhances AI assistants and agents with an intelligent memory layer, enabling personalized AI interactions. It remembers user preferences, adapts to individual needs, and continuously learns over time—ideal for customer support chatbots, AI assistants, and autonomous systems.
Key Features & Use Cases
Core Capabilities:
- Multi-Level Memory: Seamlessly retains User, Session, and Agent state with adaptive personalization
- Developer-Friendly: Intuitive API, cross-platform SDKs, and a fully managed service option
Applications:
- AI Assistants: Consistent, context-rich conversations
- Customer Support: Recall past tickets and user history for tailored help
- Healthcare: Track patient preferences and history for personalized care
- Productivity & Gaming: Adaptive workflows and environments based on user behavior
🚀 Quickstart Guide
Sign up as an agent
AI agents can mint a working Mem0 API key in under five seconds — no email, no dashboard, no OTP. Four commands end-to-end:
bash
1. Install
npm install -g @mem0/cli or: pip install mem0-cli
2. Sign up as an aTop issues
#5352Workaround: Solving time-blindness, semantic conflicts, and missing CRUD in Mem0 OSS + Qdrant56 comments · 2026-06-03#7283Faithfulness check before memory write , interested in contributing a pluggable verification hook34 comments · 2026-09-11#4956ADD-only extraction in v3 may surface stale/contradictory facts for time-sensitive attributes24 comments · 2026-04-24#5245Silent memory loss when batch embedding partially fails in V3 add pipeline22 comments · 2026-05-24#7452bug(memory): delete_all() leaves the scope's session messages, which are re-sent to the LLM on the next add()17 comments · 2026-09-25#4892Bug: concurrent AsyncMemory writes corrupt Qdrant HNSW index ('index N is out of bounds')13 comments · 2026-04-19#7376RFC: memory export interop — portable bundles with proof and chain of custody12 comments · 2026-09-18#5867ADD-only memory extraction can create conflicting memories12 comments · 2026-06-25
Discussions
#7921Memtru: reproducible checks for deleted agent memory returning after background work0 comments · 2026-11-14#7910Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-13#7902mcp-slim: Zero-dependency MCP stdio proxy for Mem0 agents (-50% to -98% schema tokens & SecretGuard)0 comments · 2026-11-12#7897Expiration boundary semantics: date-inclusive vs instant-exclusive — what breaks at the edges?2 comments · 2026-11-11#7887[RFC] Lineage tracking & permission inheritance on synthesized memory graphs0 comments · 2026-11-09#7882请问下mem0两个月没更新了,是停更了吗?1 comments · 2026-11-09#7851Scoring LongMemEval-S retrieval rankings with a standalone -score driver (no tool in the loop)0 comments · 2026-11-06#7813Cloud Alter Ego: a remote MCP connector that keeps your agent memory as Markdown files in your own cloud0 comments · 2026-11-01
Latest release
Mem0 Node SDK (v3.3.1) ts-v3.3.1 2026-09-25Bug Fixes: - Config (OSS): ConfigManager no longer injects OpenAI's default baseURL and model into non-OpenAI LLM providers. The defaults now apply only to openai and openai_structured, so a DeepSeek, xAI, or other provider config without an explicit baseURL or model falls back to that provider's own defaults and env vars (DEEPSEEK_API_BASE, XAI_API_BASE, ...) instead of pointing at OpenAI with an OpenAI model name (7350) - Vector Stores: Turbopuffer filters now apply every operator (eq, ne, gt, gte, lt, lte, in, nin). Only the range operators were read before, so eq, ne, in, and nin were si