#5,152 of 5,656 by stars
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!
- Stars
- 10,812
- Forks
- 1,009
- Created
- 1y ago
- Last push
- 3d ago
Momentum
- Per day
- +7
- Per 7 days
- +18
- Per 30 days
- +82
- Rank, 7 days
- -9
Stars over time
View as table
| Date | Stars |
|---|---|
| Sep 17, 2026 | 10,725 |
| Oct 5, 2026 | 10,782 |
| Oct 12, 2026 | 10,794 |
| Oct 19, 2026 | 10,812 |
Understand this repo
Open it in a tool that explains, diagrams or digests the code.
- Explain A plain-language walkthrough of what the project is and does
- Diagram An interactive architecture diagram of the codebase
- Ingest for AI The whole repository as one text digest to paste into an AI assistant
- Reverse prompt A prompt describing how to rebuild the project
These open independent third-party sites, which may be slow or unavailable for very large repositories.
Similar repositories
Ranked by how many distinctive topics they share with this one.
- 2508
- 3133
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
- 3468
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
- 225
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
- 3461
Python Implementation of Reinforcement Learning: An Introduction
- 1920
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。