MemOS

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

MemTensor/MemOS

View on GitHub ↗

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

MemOS grew +4.4% in the last 30 days, ranks 83rd of 1,535 in Memory & Knowledge (RAG), actively maintained, last commit today.

Star trajectory

124 days tracked
2026-06-2112.1k stars today2026-10-25
Momentum

+4.4% in 30d, above the Memory & Knowledge (RAG) median of +0.9%.

Maintenance

Last commit today, fresher than the median of 16d.

How it compares in Memory & Knowledge (RAG)

MemOS
12.1k
stars
+4.4% 30d
commit today
Memory & Knowledge (RAG) median
382
stars
+0.9% 30d
commit ~16d ago
Leader · markitdown
192k
stars
+2.7% 30d
commit yesterday

Ranked 83rd of 1,535 by stars.

Language
TypeScript
License
Apache License 2.0
Contributors
103
Forks
1.1k
Watchers
51
Open issues
69
Releases
59
Created
2025-07-06
Stars this week
+163

You've seen where MemOS stands today.

Get the moves before everyone else: the 5 Memory & Knowledge (RAG) repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain MemOS?

Claim this page to add your own call-to-action.

Claim this page