StableVery rare
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!
- Owner
- OpenPipe (organization)
- Stars
- Stars: 10,836
- Forks
- Forks: 1,009
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- llmslorareinforcement-learningagentagentic-aigrporlqwenqwen3
- Tier
- Stable (5,000 to 19,999 ★) What this tier means
More repos by OpenPipe
All 4 repos by OpenPipe- OpenPipe/OpenPipeStars: 2,836TypeScriptRC
- OpenPipe/pii-redactionStars: 116PythonPrototype
- OpenPipe/deductive-reasoningStars: 112PythonPrototype
Nearby in Python
All Python repos- x-hw/amazing-qrStars: 10,849PythonStable
- Flowseal/tg-ws-proxyStars: 10,849PythonStable
- gleitz/howdoiStars: 10,840PythonStable
- cumulo-autumn/StreamDiffusionStars: 10,827PythonStable
- Acly/krita-ai-diffusionStars: 10,817PythonStable
- databrickslabs/dollyStars: 10,812PythonStable