aaif-goose/goose

Analysis updated 2026-06-20

★ 43,936RustAudience · developerComplexity · 3/5LicenseSetup · moderate

Mindmap

mindmap
  root((Goose AI Agent))
    What it does
      Runs shell commands
      Edits files
      Browses the web
      Runs tests
    AI providers
      Anthropic Claude
      OpenAI GPT
      Google Gemini
      Ollama local
    Interfaces
      Desktop app
      CLI terminal
      Embeddable API
    Extensions
      MCP protocol
      70 plus tools

mindmap root((Goose AI Agent)) What it does Runs shell commands Edits files Browses the web Runs tests AI providers Anthropic Claude OpenAI GPT Google Gemini Ollama local Interfaces Desktop app CLI terminal Embeddable API Extensions MCP protocol 70 plus tools

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Give goose a plain-English goal like 'set up my project, install dependencies, and run the tests' and let it execute the full workflow autonomously.

USE CASE 2

Use goose as a research agent to browse the web, gather information from multiple sources, and produce a written summary document.

USE CASE 3

Connect goose to your database via an MCP extension and have it query, analyze, and generate reports from your data.

USE CASE 4

Automate repetitive file management, code refactoring, or documentation tasks by describing what you want done in natural language.

What is it built with?

Rust

How does it compare?

	aaif-goose/goose	helix-editor/helix	fuellabs/fuels-rs
Stars	43,936	44,254	43,217
Language	Rust	Rust	Rust
Setup difficulty	moderate	easy	moderate
Complexity	3/5	2/5	4/5
Audience	developer	developer	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires an API key from at least one supported AI provider such as Anthropic or OpenAI, or a locally running Ollama instance.

Free to use for any purpose including commercial, as long as you include the Apache 2.0 license notice.

In plain English

Goose is an open-source, general-purpose AI agent that runs locally on your machine and can do far more than just suggest code. Unlike typical AI coding assistants that sit in your editor and offer completions, goose can autonomously install software, execute shell commands, edit files, run tests, browse the web, conduct research, and automate multi-step workflows. You give it a goal and it figures out the sequence of actions to complete it. The core concept is that goose acts as an agent, it has tools it can call, memory of what it has done, and the ability to loop through tasks until a goal is satisfied. It is not limited to programming: you can use it to write documents, analyze data, manage files, or automate any task your computer can perform. Goose connects to over 15 AI providers, including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and AWS Bedrock, so you can use it with API keys or your existing Claude, ChatGPT, or Gemini subscriptions. It supports the Model Context Protocol (MCP), an open standard that defines how AI agents can communicate with external tools and data sources, giving it access to over 70 extensions for databases, web browsers, code environments, and more. It also supports the Agentic Communication Protocol (ACP) for provider connections. The project is available as a native desktop application for macOS, Linux, and Windows, as a full-featured CLI for terminal workflows, and as an embeddable API for building your own tools on top of it. The core is written in Rust for performance and cross-platform portability. Goose was originally developed by Block (the company behind Square and Cash App) and has since moved to the Agentic AI Foundation under the Linux Foundation. It is licensed under Apache 2.0.

Copy-paste prompts

Prompt 1

I want to use goose to automate my development environment setup. Write a goose session prompt that clones a repo, installs dependencies, sets environment variables, and runs the test suite.

Prompt 2

How do I connect goose to my local Postgres database using an MCP extension and then ask it to generate a data summary report?

Prompt 3

Using goose with the Anthropic Claude API, help me set up a workflow that monitors a folder for new CSV files and automatically analyzes each one.

Prompt 4

What MCP extensions should I enable in goose to build a web research agent that searches, browses pages, and saves findings to a markdown file?

Prompt 5

Show me how to run goose from the command line to refactor all Python files in my project to add type hints.

Frequently asked questions

What is goose?

Open-source AI agent that runs on your machine and can autonomously install software, edit files, run tests, browse the web, and complete multi-step tasks using any major AI provider.

What language is goose written in?

Mainly Rust. The stack also includes Rust.

What license does goose use?

Free to use for any purpose including commercial, as long as you include the Apache 2.0 license notice.

How hard is goose to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is goose for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub aaif-goose on gitmyhub

Verify against the repo before relying on details.