OP
OpenRLHF
Reinforcement Learning·infrastructure·open·#485 of 884·+41·Rising
70.0
Low
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%
60.5
Maintenance
30%
81.6
Friction
20%
98.0
Ecosystem
15%
45.3
Momentum
0.59Rising
7d change -0.13
High confidenceIn Reinforcement Learning
Ranked #15 of 32