TrendingRisingGemsRadarToolboxCategories

Repository

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!

Open source WebsiteAI & agents PythonApache-2.0

Stars

11k

Today

+2

last 24 hours

This week

+2

Forks

1k

Clone

git clone https://github.com/OpenPipe/ART.git

Star growth

2026-10-18: +2 (today so far)2026-10-18todaymax +2/day
Stars gained per day. Tracking since 2026-10-18; the lighter bar is today so far.
#llms#lora#reinforcement-learning#agent#agentic-ai#grpo#rl#qwen#qwen3
Created
2025-03-10
Last commit
2026-10-15
Gained since tracking
+2

Similar in AI & agents

Updated Sun, 18 Oct 2026 15:32:30 GMT · description from the project itself