ShishirPatil/gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

62
/ 100
Established

Provides fine-tuned models and the Berkeley Function Calling Leaderboard for benchmarking LLMs on API invocation across 1,600+ real-world APIs with retrieval-augmented training for improved accuracy. Includes GoEx, a runtime engine with post-facto validation and damage confinement for safely executing LLM-generated API calls and code, plus OpenFunctions-V2 supporting parallel execution and multiple data types. Expands beyond single-turn scenarios with multi-turn agentic benchmarks featuring web search, memory management, and error recovery evaluation.

12,759 stars. Actively maintained with 2 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

12,759

Forks

1,334

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ShishirPatil/gorilla"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.