OP
OpenRLHF
Reinforcement Learning·infrastructure·open·#438 of 944·+33·Surging
72.5
Moderate
High confidence
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
Pillar Breakdown
Adoption
35%
64.4
Maintenance
30%
84.5
Friction
20%
99.8
Ecosystem
15%
45.1
Momentum
0.76Surging
7d change +1.38
High confidenceIn Reinforcement Learning
Ranked #14 of 32