OpenPipe/
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!
by OpenPipe Python Apache-2.0 licence 1,015 forks Created Mar 2025 View on GitHub
- Stars
- 10,851
- 77% of OpenPipe's stars
- Rank
- #5,214
- of 847,083 repos, top 0.6%
- In Python
- #972
- of 172,210 repos, top 0.6%
Among 847,083 repos
10k–16k stars: 2,591 repos, including ART
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #5,212
- Next milestone
- +27,294 stars to reach the top 0.1%
- Popular
- One of 5,747 repos with 10k+ stars
- Yearly average
- 6,492 stars a year since Mar 2025