gorilla logo

gorilla

ShishirPatil/gorilla

Training and Evaluating LLMs for Function Calls (Tool Calls)

GraphCanon updated Oct 16, 2026 · GitHub synced Oct 16, 2026

13k stars1.4k forksLast push Apr 13, 2026 Python Apache-2.0

Decision brief

Unverified catalog guidance: Gorilla specializes in training and evaluating large language models (LLMs) to perform function calls or tool usages.

Good fit when

  • Unverified catalog guidance: You should consider using Gorilla if you need a comprehensive framework for developing LLMs capable of leveraging external functions effectively.
  • Unverified catalog guidance: If your project requires interactive testing through web interfaces like Colab and Gradio, Gorilla provides dedicated demos that can help streamline this process.

Avoid when

  • Unverified catalog guidance: Avoid Gorilla if your primary focus is not on function calling or tool usage capabilities for LLMs; another model-specific framework may better fit your needs.
  • Unverified catalog guidance: If the lack of a direct comparison tool to other models' function-calling performance is critical in your decision process, and you find no suitable alternatives listed on their leaderboard.
Pricing:
freemium
Requirements:
Gorilla works best with Python environments and requires installation through pip or local repository cloning.

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (186d since push)
As of Oct 16, 2026
Provenance
Not a fork · Personal account
As of Oct 16, 2026
Security (OSV)
No lockfile
As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install gorilla-cli

README installation instruction · observed Oct 16, 2026

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A toolset for training and evaluating large language models with functions calls or tool usages.

Capability facts

Docker
Docker configuration present

Source: dockerfile:.devcontainer/raft/Dockerfile · Oct 16, 2026

CLI
Declared CLI entrypoint

Source: berkeley-function-call-leaderboard/pyproject.toml:[project.scripts] · Oct 16, 2026

MCP server
Unknown; MCP server not established by this scan

Source: repo_scan · Oct 16, 2026

Languages
python, javascript

Source: github.language+agent-arena/client/package.json+berkeley-function-call-leaderboard/pyproject.toml · Oct 16, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Documented Python runtime (not runtime-tested)Python

Source: README excerpt (readme_declaration_v2, Oct 16, 2026)

pip install gorilla-cli
Source link

Tags

README

Quick Start Try Gorilla in your browser: 🚀 Gorilla Colab Demo: Try the base Gorilla model 🌐 Gorilla Gradio Demo: Interactive web interface 🔥 OpenFunctions Colab Demo: Try the latest OpenFunctions model 🎯 OpenFunctions Website Demo: Experiment with function calling 📊 Berkeley...

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.