goose

Overview

goose is a general-purpose, open source AI agent that runs on your machine. It is available as a native desktop app for macOS, Linux, and Windows, a CLI for terminal workflows, and an API for embedding. Built in Rust, it supports code, research, writing, automation, data analysis, and other tasks.

Key Features

• Native desktop app for macOS, Linux, and Windows, plus a CLI and an API.
• Connect to 70+ extensions such as databases, APIs, browsers, GitHub, and Google Drive via the Model Context Protocol open standard.
• Works with 15+ model providers, including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock, using API keys or existing Claude, ChatGPT, or Gemini subscriptions via ACP.
• Recipes capture workflows as portable YAML configs for sharing with teams and running in CI.
• Subagents can handle tasks in parallel, including code review, research, and file processing.
• Security features include prompt injection detection, tool permission controls, sandbox mode, and an adversary reviewer that watches for unsafe actions.

Use Cases

• Code-related tasks such as installing, executing, editing, and testing with supported LLMs.
• Research, writing, automation, and data analysis.
• Sharing portable workflows with a team or running them in CI using recipes.
• Using extensions to connect goose to databases, APIs, browsers, GitHub, Google Drive, and more.

Getting Started

• Download the desktop app for macOS, Linux, or Windows.
• Install the CLI using the provided shell script.

Before You Adopt

• License: Apache-2.0. Review its terms before using, modifying, or distributing the project.
• goose depends on external model providers; the source lists 15+ providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock.
• goose can use community-built MCP extensions, an external extension ecosystem users can browse and add to.