- Repository
- https://github.com/OpenPipe/ART
- Homepage
- https://art.openpipe.ai
- Owner
- OpenPipe (Organization)
- Stars
- 10,807
- Forks
- 1,008
- Open issues
- 169
- Language
- Python
- License
- Apache-2.0
- Created
- 2025-03-10
- Last push
- 2026-10-15
- Topics
- agent, agentic-ai, grpo, llms, lora, qwen, qwen3, reinforcement-learning, rl
- Snapshot
- 2026-10-18
GitHub · #750
OpenPipe/ART
OpenPipe/ART is #750 in this GitHub directory, with 10,807 stars. 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!