OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Gorilla

Gorilla is an open-source Python project for training and evaluating large language models that invoke functions, tools and external APIs from natural-language requests. It provides model inference and evaluation code alongside APIBench resources for training and testing tool-call behavior.

Independent OpenViST project profile, based on linked sources.

Gorilla — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Gorilla when an LLM must select or generate calls to functions and APIs, or when you need to evaluate that behavior rather than only generate free-form text.

Who it is for

  • AI engineers building assistants that call external APIs
  • Researchers evaluating LLM function-calling performance
  • Developers experimenting with API documentation, tool selection and structured calls

Documented uses

  • Train models to generate structured function calls
  • Evaluate model behavior on tool-call tasks
  • Connect an LLM assistant to external APIs
  • Run experiments using API-oriented datasets and documentation
Before you choose

Requirements & limits

The repository is public, active and Apache-2.0 licensed. It is written in Python. The evidence does not specify account, pricing or service-availability requirements.

  • The project focuses on model training, inference and evaluation for tool calls, not a general-purpose end-user assistant.
  • Its documented ecosystem includes OpenAI API and OpenAI function topics.
  • The repository includes APIBench, inference material and evaluation code for API-connected language models.
  • Related Gorilla work includes multi-turn and multi-step function-calling evaluation through the Berkeley Function Calling Leaderboard.
  • GoEx extends the project area toward runtime handling of LLM-generated actions, including API calls, with post-facto validation, undo and damage-confinement abstractions described in the repository updates.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
GorillaTrain models to generate structured function callsCloud, Self-hostedThe repository is public, active and Apache-2.0 licensed. It is written in Python. The evidence does not specify account, pricing or service-availability requirements.
HyperposeCustomize pose-estimation architectures and datasets.Docker, Linux, macOS, Windows
Multi Task NlpDefine multiple tasks and their data and model settings in a YAML file.Linux, macOS, WindowsThe project is an open-source library under the Apache-2.0 license, distributed through its public GitHub repository.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
ShishirPatil/gorilla · Official homepage title · retained in its source language
How we review sourcesSuggest a correction