OP
OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Growth
- Last 24 hours
- +3
- stars
- Last 7 days
- +13
- stars
- Last 30 days
- +110
- stars
- Total stars
- 10,797
- 10.7k a month ago
- Forks
- 1,005
- 0 contributors
Star history
Last 12 weeks · weekly cumulative stars · computed from public GitHub star events
Rank in its topics
| Topic | Today | This week | This month |
|---|---|---|---|
| Python | – | – | #478of 639 |
| AI agents | – | – | #497of 542 |
| LLM | – | – | #361of 431 |
| Machine learning | – | – | #107of 170 |
README
ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Upstar hasn’t fetched this README yet. Read it on GitHub.