FreeAIRepo
Agents & automation

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!

Apache-2.0Python
Stars
11k
Forks
1.0k
Open issues
80
Last push
today

About ART

ART is a free, open-source AI agent tool by OpenPipe, written mainly in Python. 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!. It has 11k GitHub stars and 1.0k forks, and was last updated today. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
10,819
Last update
today
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Agents & automation tools →

ART FAQ

Is ART free?

Yes. ART is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does ART run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does ART need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is ART still maintained?

Yes. It was last updated today and has 80 open issues on GitHub.

What are alternatives to ART?

Similar free, open-source tools include hermes-agent, paperclip, ruflo, ai-agent-book.

Related topics