# Goose

> Open-source AI agent for your machine — desktop app, CLI, and API

- Category: AI Coding / Autonomous Coding Agents
- Language: Rust
- Licence: Apache-2.0
- Repository: https://github.com/aaif-goose/goose
- Website: https://goose-docs.ai/
- Canonical page: https://ai-tldr.dev/tools/goose/

## In short

Goose is a general-purpose, open-source AI agent that runs locally on your own machine. It is not limited to coding — you can use it for research, writing, automation, data analysis, or any task you need to get done. It sits in the Autonomous Coding Agents category of the AI Coding tools and is open-source, written in Rust and licensed Apache-2.0.

## Overview

Goose is a general-purpose, open-source AI agent that runs locally on your own machine. It is not limited to coding — you can use it for research, writing, automation, data analysis, or any task you need to get done.

Built in Rust for performance and portability, Goose ships as a native desktop app for macOS, Linux, and Windows, a full CLI for terminal workflows, and an API you can embed anywhere.

It works with 15+ model providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock, and connects to 70+ extensions through the open Model Context Protocol (MCP) standard. Goose is part of the Agentic AI Foundation (AAIF) at the Linux Foundation.

## What it does

- Runs entirely on your own machine as a native app, CLI, or embeddable API
- General-purpose: handles code, research, writing, automation, and data analysis
- Works with 15+ LLM providers (Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, Bedrock, and more)
- Connects to 70+ extensions via the Model Context Protocol (MCP) open standard
- Use API keys or your existing Claude, ChatGPT, or Gemini subscriptions through ACP
- Build your own custom distribution with preconfigured providers, extensions, and branding

## Getting started

You can run Goose as a native desktop app or from the terminal. Download the desktop app for macOS, Linux, or Windows, or install the CLI with a single command.

1. Install the CLI

   Download and run the CLI install script to set up Goose in your terminal.

```bash
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash
```

2. Or download the desktop app

   Prefer a graphical experience? Download the native desktop app for macOS, Linux, and Windows from the installation page, then follow the quickstart guide to connect a model provider.

## When to use it

- Automate coding tasks and migrate or refactor projects from the terminal
- Run research, writing, or data-analysis workflows with a local AI agent
- Embed an AI agent into your own tools via the Goose API
- Build a custom, branded agent distribution with preconfigured providers and MCP extensions