Goose
- coding-agent
- macOS
- Linux
- Windows
- #agent
- #open-source
- #desktop
- #mcp
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
About
What is codename goose?
codename goose is a local, extensible, open-source AI agent that automates engineering tasks from start to finish. It runs on your machine as both a desktop app and a CLI, and works with any LLM while integrating seamlessly with Model Context Protocol (MCP) servers.
How to use codename goose?
Install codename goose using the official quickstart guide and documentation available at the project website. After installation, you can run it via the desktop application or command-line interface, connect any LLM provider, and attach MCP servers to extend its capabilities.
Key features of codename goose
- Local execution (runs on your machine)
- Works with any large language model
- Seamless MCP server integration
- Desktop app and CLI availability
- Open source under Apache 2.0 license
Use cases of codename goose
- Build entire projects from scratch autonomously
- Write, execute, and debug code end-to-end
- Orchestrate complex engineering workflows
- Interact with external APIs during task execution
- Prototype ideas and refine existing codebases
FAQ from codename goose
What can codename goose do?
codename goose can automate complex development tasks including building projects, writing and executing
Highlights
- Open-source, locally running AI agent
- Extensions system built around MCP
- CLI and desktop experiences
- Bring your own models and tool servers
Details
- Author
- block
- GitHub stars
- 13,542
- Category
- coding-agent
- Platforms
- macOS, Linux, Windows
- Website
- block.github.io/goose/
- Docs
- Official docs
- Repository
- block/goose
- Config path
Goose config / Extensions UI
Add MCP extensions in Goose
Config file: Goose config / Extensions UI
- Install Goose (desktop or CLI) from the official docs
- Open Settings → Extensions (or run goose configure)
- Add an MCP server with command + args (or a remote URL)
- Start a session and confirm the extension tools are listed
Note: Goose can mix built-in extensions with community MCP servers.
Example MCP config
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed"]
}
}
}Looking for servers to connect? Browse MCP servers for Goose
<div align="center">
codename goose
_a local, extensible, open source AI agent that automates engineering tasks_
<p align="center">
<a href="https://opensource.org/licenses/Apache-2.0">
<img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg">
</a>
<a href="https://discord.gg/7GaTvbDwga">
<img src="https://img.shields.io/discord/1287729918100246654?logo=discord&logoColor=white&label=Join+Us&color=blueviolet" alt="Discord">
</a>
<a href="https://github.com/block/goose/actions/workflows/ci.yml">
<img src="https://img.shields.io/github/actions/workflow/status/block/goose/ci.yml?branch=main" alt="CI">
</a>
</p>
</div>
goose is your on-machine AI agent, capable of automating complex development tasks from start to finish. 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 - _autonomously_.
Whether you're prototyping an idea, refining existing code, or managing intricate engineering pipelines, goose adapts to your workflow and executes tasks with precision.
Designed for maximum flexibility, goose works with any LLM, seamlessly integrates with MCP servers, and is available as both a desktop app as well as CLI - making it the ultimate AI assistant for developers who want to move faster and focus on innovation.
