Plain-AyI
← All projects
AI models & research

Gorilla

Research on teaching AI models to use software tools correctly, including a well-known scoreboard for comparing models.

Research-backedNew this week

What it does

Gorilla is a research project from the University of California, Berkeley about "function calling": getting an AI model to pick the right software tool and use it properly when you ask for something in plain words.

The project includes its own fine-tuned models, a large collection of software tool descriptions for training, and the Berkeley Function Calling Leaderboard, which scores how well different AI models use tools.

It also covers related work, such as a system for safely running and undoing actions an AI takes, and a command-line helper that turns plain requests into terminal commands.

Who it's for

AI researchers and developers who want to measure or improve how well models use tools and APIs.

Can I use it without coding?

Developers only. Mostly research code, models and datasets; there are browser demos to try the models. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Web browser
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

Where people are talking about it