MemOS logo

MemOS

RAG & Memory 7.0/10 Strong

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

MemOS scores 7/10 (Strong) in RAG & Memory.

Language TypeScript License Apache-2.0 Stars 10.1k★ Type library Self-host Yes Repo MemTensor/MemOS Homepage https://memos.openmem.net

Quality

Strong 7.0
Adoption 50
Activity 84
Maturity 81
Community 50
Capability 50
Show the math
Overall 7/10
value = 7/10
score = value
Adoption 5.5/10
value = 50.1/100
score = 1 + 9 * value / 100
Activity 8.6/10
value = 84.3/100
score = 1 + 9 * value / 100
Maturity 8.3/10
value = 80.9/100
score = 1 + 9 * value / 100
Community 5.5/10
value = 49.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100

Key metrics

10.1k★ GitHub stars
506/90d Recent commits
17 devs/90d Recent contributors
12mo Project age
active Last commit

Gotchas

No gotchas documented yet. Contribute one if you know a constraint we missed.

Labels

  • New project

    New (12mo)

    Created within the last year — promising but less battle-tested.

  • Self-hosted

    Self-hosted

    You deploy and operate it yourself; there is no hosted option here.

memory agents persistent hybrid-retrieval