← All projects
Training & fine-tuning

Reef

Infrastructure that lets AI agents keep improving from how you interact with them.

New this week

What it does

Reef is open-source infrastructure for AI agents that keep getting better over time. It connects serving an agent, collecting feedback, learning from it, and delivering updated versions.

It can improve an agent by training the model's weights, or by improving the agent's prompts, rules and skills, while the agent stays live through updates.

Its makers describe a repeating cycle of serving requests, matching feedback, producing an update, and publishing the ones that pass checks.

Who it's for

Developers and researchers building AI agents that learn and improve continuously.

Can I use it without coding?

Developers only. It is infrastructure set up and used by writing code, and training needs suitable hardware. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Server
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe