OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
OpenRLHF scores 6.3/10 (Solid) in Fine-Tuning.
Language Python License Apache-2.0 Stars 9.7k★ Type heavyweight Self-host Yes Repo OpenRLHF/OpenRLHF Homepage https://openrlhf.readthedocs.io
Quality
Solid 6.3
Adoption 50
Activity 57
Maturity 96
Community 50
Capability 50
Show the math
Overall 6.3/10
value = 6.3/10
score = value
Adoption 5.5/10
value = 49.7/100
score = 1 + 9 * value / 100
Activity 6.1/10
value = 56.6/100
score = 1 + 9 * value / 100
Maturity 9.6/10
value = 95.7/100
score = 1 + 9 * value / 100
Community 5.5/10
value = 50.3/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
9.7k★ GitHub stars
30/90d Recent commits
5 devs/90d Recent contributors
2.9y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
rlhf ray vllm ppo agents