Skip to content

Goose

Website GitHub License
block.github.io/goose block/goose Apache 2.0

Goose is a local, extensible, open source AI agent that automates engineering tasks from start to finish.

Goose is your on-machine AI agent, capable of automating complex development tasks autonomously. More than just code suggestions, Goose can build entire projects from scratch, write and execute code, debug failures, orchestrate workflows, and interact with external APIs. Whether you're prototyping an idea, refining existing code, or managing intricate engineering pipelines, Goose adapts to your workflow and executes tasks with precision.

Key Features

  • Autonomous Development Tasks: Goose can build entire projects from scratch, write and execute code, debug failures, and manage complex engineering workflows without requiring constant supervision.
  • Multi-LLM Support: Designed for maximum flexibility, Goose works with any LLM and supports multi-model configuration to optimize performance and cost for different types of tasks.
  • MCP Server Integration: Seamlessly integrates with MCP (Model Context Protocol) servers, allowing for extended functionality and integration with external tools and APIs.
  • Dual Interface Options: Available as both a desktop application and a command-line interface, making it accessible for different developer preferences and workflows.
  • Local and Extensible: Runs locally on your machine for privacy and security, while being extensible through its open architecture to adapt to your specific development needs.

Goose is a powerful and flexible tool for any developer who wants to leverage autonomous AI assistance in their daily workflow. Its ability to handle complete development tasks, multi-model support, and availability in both GUI and CLI formats make it a comprehensive solution for AI-assisted software engineering.

Installation

CLI

The Goose CLI can be installed using pipx.

pipx install goose-ai

Desktop App

A desktop application is available for Mac and Windows. You can download it from the Goose website.

Quickstart

  1. Install Goose using one of the methods above.
  2. Configure Goose with your preferred LLM by obtaining the necessary API keys.
  3. Start a Goose session: bash goose session start
  4. Interact with the AI agent to automate tasks.
  • Website: https://block.github.io/goose/
  • GitHub: https://github.com/block/goose
  • Documentation: https://block.github.io/goose/docs/intro

Tutorials

CC0 1.0 Universal  ・  Eleanor Berger (AI Expertise) and the OSS AI SWE Community