TypeScript · Apache-2.0
MemTensor/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.
★ 12.3k
Stars
1.1k forks · 154 open issues
+13/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
48.6
Momentum / 100
see the breakdown below
16mo ago
Created
last push 4d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 21.8 | +13/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.73× the monthly pace |
| Freshness | 15 | 14.9 | last push 4d ago; decays to zero at 180 days |
| Scale | 15 | 11.9 | 12.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 48.6 | sum of the above |
Detail
| Topics | agentagentic-aiaiai-agentschatgptclaudedeepseek-harnessdsh-pluginhermesllmlong-term-memorymcpmemorymemory-managementopenclawragself-evolvingskillstoken-savings |
| Matched on | AI Agents (agentic-ai) RAG (rag) |
| Short window | +90 stars over 7 days = 12.9/day |
| Long window | +460 stars over 26 days = 17.7/day |
| Lifetime average | 25.17 stars/day over 487 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |