Python · MIT
Fergana-Labs/stash
Open-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.
★ 342
Stars
45 forks · 33 open issues
+2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
31.5
Momentum / 100
see the breakdown below
8mo ago
Created
last push 5d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 2.1 | +2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 7.3 | last week ran 1.49× the monthly pace |
| Freshness | 15 | 14.8 | last push 5d ago; decays to zero at 180 days |
| Scale | 15 | 7.4 | 342 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 31.5 | sum of the above |
Detail
| Topics | agent-collaborationaiartifactsclaude-codeclicodexcoding-agentcontext-engineeringcontinual-learningknowledge-basemcpmemorymulti-agentpersonal-knowledge-basepersonal-knowledge-managementsemantic-searchskillswikiworkspace |
| Matched on | RAG (semantic-search) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +5 stars over 26 days = 0.2/day |
| Lifetime average | 1.28 stars/day over 266 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |