Tool profile

OpenRLHF/OpenRLHF

stable

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

large-language-modelsproximal-policy-optimizationraylibreinforcement-learningreinforcement-learning-from-human-feedbacktransformersvisual-language-modelsvllm

Velocity score

0.92/ 10

[STARS]

9.5k

[FORKS]

940

[CONTRIBUTORS]

[LAST_COMMIT]

7d ago

OPEN_ON_GITHUB

30-day stars

0.92/ 10 score

last 36d

[SIGNAL_TRACE / 36_PT]

Score breakdown

765/ 1000

inference · OpenRLHF/OpenRLHF

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

968

[INSTALL_VEL]

498

[ACTIVITY]

547

[COMMUNITY_SIGNAL]

1000

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).