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!
OpenPipe/ART
View on GitHub ↗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!
ART grew +0.5% in the last 30 days, ranks 17th of 203 in Fine-Tuning (LoRA / PEFT), actively maintained, last commit yesterday.
Star trajectory
123 days tracked+0.5% in 30d, above the Fine-Tuning (LoRA / PEFT) median of +0.1%.
Last commit yesterday, fresher than the median of 258d.
How it compares in Fine-Tuning (LoRA / PEFT)
Ranked 17th of 203 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 28
- Forks
- 1k
- Watchers
- 67
- Open issues
- 83
- Releases
- 60
- Created
- 2025-03-10
- Stars this week
- +16
You've seen where ART stands today.
Get the moves before everyone else: the 5 Fine-Tuning (LoRA / PEFT) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.