Python · MIT
datamllab/HarborRL
An end-to-end framework for Agentic Reinforcement Learning.
★ 119
Stars
9 forks · 0 open issues
+11/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
41.3
Momentum / 100
see the breakdown below
26d ago
Created
last push 9d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 20.8 | +11/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.5 | last push 9d ago; decays to zero at 180 days |
| Scale | 15 | 6.0 | 119 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 41.3 | sum of the above |
Detail
| Topics | agentagent-frameworkagenticagentic-aiagentrlcoding-agentcoding-agentsdapogrpoharborharbor-frameworkllmllm-agentsllmsppoprmreinforcement-learningreinforcement-learning-agentrlslime |
| Matched on | AI Agents (agentic-ai) |
| Short window | +67 stars over 6 days = 11.2/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 4.98 stars/day over 24 days |
| First seen here | 2026-10-30 |
| Last read | 2d ago |