Python · Apache-2.0
Human-Agent-Society/reef
Infrastructure for continually self‑improving agents
★ 7.8k
Stars
732 forks · 174 open issues
+5.9/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
42.3
Momentum / 100
see the breakdown below
2mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 16.0 | +5.9/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.54× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 11.3 | 7.8k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 42.3 | sum of the above |
Detail
| Topics | agent-infrastructureai-agentscontinual-learninginferencellmllm-trainingreinforcement-learningself-improving-agents |
| Matched on | AI Agents (ai-agents) LLM & Inference (llm) |
| Short window | +41 stars over 7 days = 5.9/day |
| Long window | +284 stars over 26 days = 10.9/day |
| Lifetime average | 117.42 stars/day over 66 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |