Goose
Goose is an open-source, general-purpose AI agent that runs locally on your machine, available as a desktop app, CLI, and API. It solves the problem of needing a versatile AI assistant for code, research, writing, automation, and data analysis, and is built in Rust for performance and portability.
🎬 Build Apps Faster with AI | Vibe Coding with Goose · goose OSS
✨ Key features
- Native desktop app for macOS, Linux, and Windows
- Full CLI for terminal workflows
- API to embed anywhere
- Works with 15+ providers including Anthropic, OpenAI, Google, Ollama
- Supports 70+ extensions via Model Context Protocol
- Part of the Linux Foundation's Agentic AI Foundation
🎯 Use cases
- Automate coding tasks and code migration
- Conduct research and writing projects
- Perform data analysis
- Automate workflows and tasks
- Embed AI agent capabilities into custom applications
📦 Installation
🧰 Requirements: Runs on macOS, Linux, or Windows; requires an API key or subscription for a supported AI provider (e.g., Anthropic, OpenAI, Google) or use local models via Ollama.
Desktop App
Download the desktop app from goose-docs.ai/docs/getting-started/installation for macOS, Linux, and Windows.
CLI
Install the CLI with:
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash
🚀 Usage
After installation, run goose in your terminal to start the CLI. For detailed usage, see the Quickstart guide.
❓ FAQ
What platforms does Goose support?
Goose provides a native desktop app for macOS, Linux, and Windows, as well as a CLI and API.
Which AI providers can I use with Goose?
Goose works with 15+ providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock. You can use API keys or existing subscriptions via ACP.
Can I extend Goose with additional tools?
Yes, Goose supports 70+ extensions via the Model Context Protocol (MCP) open standard.
Is Goose open source?
Yes, Goose is open source and part of the Agentic AI Foundation (AAIF) at the Linux Foundation.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.