by Mem0 AI
Mem0
Open-source memory layer for AI agents that enables persistent, personalised interactions by remembering user preferences, past conversations, and context across sessions.
Mem0 (pronounced "mem-zero") is the most widely adopted AI agent memory framework, backed by $24M from YC, Basis Set Ventures, and Peak XV. It adds a persistent memory layer to any AI agent or assistant with as little as three lines of code. The system uses LLM-based extraction to decide what to store, then retrieves relevant memories at query time using semantic search. The optional graph memory tier (Mem0g) adds entity extraction and relationship mapping. AWS selected Mem0 as the exclusive memory provider for their Agent SDK. Used in production by thousands of teams including integrations with CrewAI, Flowise, and Langflow natively. Free tier includes 10K memories. Pro plan at $19/mo adds graph features. Enterprise adds on-prem, SSO, HIPAA BAA, and dedicated SLA. 48,000+ GitHub stars. SOC 2 and HIPAA compliant.
Capabilities
Pros & Limitations
Editorial assessmentPros
- ✓3-line integration — works with any LLM or agent framework
- ✓AWS exclusive memory provider for their Agent SDK
- ✓48,000+ GitHub stars — largest community in agent memory space
- ✓SOC 2 and HIPAA compliant with on-prem option
- ✓Free tier includes 10K memories with no credit card required
Limitations
- ⚠Graph memory gated behind $249/mo Pro tier — steep jump from $19/mo Standard
- ⚠Vector-only retrieval on lower tiers lacks temporal reasoning
- ⚠LongMemEval score of 49% trails some newer memory frameworks
- ⚠LLM extraction pipeline can miss context the model deems unimportant
Technical Details
Similar agents
Commercial
Industries
Rating
Editorial score
Leave a review
Never displayed publicly.
Agent Stacks
See workflow stacks that feature Mem0 — curated and community-verified multi-agent setups.
Is this your tool?
Claim this listing to update your details and get a Verified badge.
Claim this listing →