Python · Apache-2.0
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
★ 10.1k
Stars
1.1k forks · 411 open issues
+2.6/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
37.7
Momentum / 100
see the breakdown below
3y ago
Created
last push 5d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 10.6 | +2.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.7 | last week ran 1.05× the monthly pace |
| Freshness | 15 | 14.8 | last push 5d ago; decays to zero at 180 days |
| Scale | 15 | 11.6 | 10.1k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 37.7 | sum of the above |
Detail
| Topics | large-language-modelsproximal-policy-optimizationraylibreinforcement-learningreinforcement-learning-from-human-feedbacktransformersvisual-language-modelsvllm |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +18 stars over 7 days = 2.6/day |
| Long window | +64 stars over 26 days = 2.5/day |
| Lifetime average | 8.49 stars/day over 1,194 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |