About goose
Overview
goose is a general-purpose AI agent that runs on your machine. It handles research, writing, automation, data analysis, and anything else you need to get done, not just code. The product ships as a native desktop app for macOS, Linux, and Windows, a full CLI for terminal workflows, and an API to embed it anywhere, all built in Rust for performance and portability.
goose connects to 70+ extensions for databases, APIs, browsers, GitHub, and Google Drive through the Model Context Protocol open standard. You can add skills or build your own extension, and add interactive UI inside goose Desktop via MCP Apps. The project belongs to the Agentic AI Foundation at the Linux Foundation.
Key Benefits
- Runs locally on your machine for research, writing, automation, data analysis, and code.
- Connects to 70+ extensions via the Model Context Protocol open standard.
- Works with 15+ LLM providers, including your existing Claude, ChatGPT, or Gemini subscriptions via ACP.
- Captures workflows as portable YAML recipes you can share with your team or run in CI.
- Adds security controls such as prompt injection detection, tool permission controls, sandbox mode, and an adversary reviewer.
- Renders interactive buttons, forms, and visualizations inside goose Desktop through MCP Apps.
How It Works
Download the desktop app for macOS, Linux, or Windows, or install the CLI with a single curl command. Add extensions for the databases, APIs, and tools you use, then choose a model from any of 15+ providers using an API key or an existing subscription. Save repeatable work as recipes to rerun or share, and spawn independent subagents to handle parallel tasks while the main conversation stays clean.
Use Cases
- Developers run the CLI for terminal workflows and connect from Zed, JetBrains, or VS Code by using goose as an ACP server.
- Teams capture workflows as YAML recipes and share them so everyone runs the same process.
- CI pipelines run recipes as portable configs that include instructions, extensions, parameters, and subrecipes.
- Data analysts connect databases and APIs through extensions and analyze data with a local agent.
- Researchers and writers use the general-purpose agent for tasks beyond code.
- Builders create MCP Apps that render interactive UI inside goose Desktop.
Why Choose This Product
goose is open source and built in the open, with governance under the Agentic AI Foundation at the Linux Foundation, which keeps the project vendor-neutral and community-governed. It was one of the earliest adopters of the Model Context Protocol and holds one of the deepest integrations in the ecosystem, with 70+ documented extensions. An active community of developers and users builds extensions, shares recipes, and contributes code.
goose Pricing
Pricing extracted from the product website and may change. Check the source for current details.