Name: OpenPipe/ART
Rating: 5 (10718 reviews)
Author: OpenPipe

Git

OpenPipe / ART

Compare

Python

10.7kstars

983forks

Activity

AI Agents

LLM Infra

ML Frameworks

Repository Trajectory

Trended #9 on daily

August 27, 2025

Trended #12 on monthly

August 16, 2025

First tracked on GitTrend

August 16, 2025

Similar Projects

Select up to three alternatives to compare with this repository:

unslothai/unslothLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

76.2k

6.9k

microsoft/agent-lightningThe absolute trainer to light up AI agents.

18.1k

1.6k

1Panel-dev/MaxKB🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。

22.8k

3.1k

google/adk-pythonAn open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

21.5k

radixark/milesMiles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

2.9k

494

embabel/embabel-agentAgent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

4.4k

433

Loading README...

Contributors

Git

Languages

Python

92%

Jupyter Notebook

About

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

art.openpipe.ai

Topics

agent

agentic-ai

grpo

kimi-ai

llms

lora

qwen

qwen3

reinforcement-learning

Readme

Activity

10.7kstars(61/day)

983forks

Contributors

Git

Languages

Python

92%

Jupyter Notebook