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.
Install the CLI
Download and run the CLI install script to set up Goose in your terminal.
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bashOr 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.
Commands and code are distilled from the project's own documentation — always check the official repo for the latest.
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
How Goose compares
Goose alongside other open-source autonomous coding agents tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| opencode | ★ 209k | OpenCode is an open source AI coding agent that runs in your terminal, with built-in build and plan agents and an optional desktop app. |
| Claude Code | ★ 147k | Anthropic's agentic coding tool for the terminal, IDE and GitHub: it understands your codebase, executes routine tasks, explains code and handles git workflows from natural-language commands. |
| OpenAI Codex | ★ 125k | OpenAI's cloud and CLI coding agent that writes features, fixes bugs, and proposes code changes across a repo, running tasks in parallel. |
| Pi | ★ 107k | Minimal terminal coding agent harness with four built-in tools, extended through TypeScript extensions, skills and prompt templates instead of forks. |
| Gemini CLI | ★ 107k | An open-source command-line AI agent from Google that connects your terminal to Gemini models for reading code, editing files, running shell commands, and searching the web. |
| autoresearch | ★ 96.4k | Karpathy's minimal harness that hands a coding agent a single-GPU LLM training script and lets it run fixed five-minute experiments, keeping or discarding each change on its own. |
| OpenHands | ★ 88.5k | An open-source AI software-development agent that plans tasks, edits files, runs commands, and tests code, usable from a terminal CLI, a local web GUI, or a Python SDK. |
| Goose | ★ 54.5k | Open-source AI agent for your machine — desktop app, CLI, and API |