Mem0
Universal memory layer for AI Agents
Mem0 scores 8.2/10 (Strong) in RAG & Memory.
Language Python License Apache-2.0 Stars 60k★ Type library Self-host Yes Repo mem0ai/mem0 Homepage https://mem0.ai
Quality
Strong 8.2
Adoption 70
Activity 89
Maturity 96
Community 71
Capability 67
Show the math
Overall 8.2/10
value = 8.2/10
score = value
Adoption 7.3/10
value = 69.5/100
score = 1 + 9 * value / 100
Activity 9/10
value = 89.4/100
score = 1 + 9 * value / 100
Maturity 9.7/10
value = 96.2/100
score = 1 + 9 * value / 100
Community 7.4/10
value = 71.4/100
score = 1 + 9 * value / 100
Capability 7/10
value = 66.9/100
score = 1 + 9 * value / 100
Key metrics
60k★ GitHub stars
351/90d Recent commits
32 devs/90d Recent contributors
LoCoMo J 66.9% LoCoMo LLM-as-a-Judge (J) score Overall LLM-as-a-Judge accuracy on the LOCOMO long-term conversational memory benchmark, base Mem0 config (graph variant reaches 68.44). Source: Mem0 paper, arxiv.org/html/2504.19413v1 (results table).
3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
memory agents personalization long-term