aaif-goose/goose

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

What it solves

It provides a general-purpose AI agent that runs locally on your machine to handle a wide variety of tasks, including coding, research, writing, automation, and data analysis.

How it works

Built in Rust for performance, goose is available as a desktop application (macOS, Linux, Windows), a command-line interface (CLI), and an API. It integrates with over 15 AI providers (such as Anthropic, OpenAI, Google, Ollama, and OpenRouter) and supports the Model Context Protocol (MCP) to connect to more than 70 extensions.

Who it’s for

Developers and users who want a versatile, open-source AI agent that can be integrated into their local workflows via a GUI or terminal.

Highlights

  • Native desktop app for Windows, macOS, and Linux.
  • Supports 15+ LLM providers and API keys or existing subscriptions.
  • Compatible with the Model Context Protocol (MCP) for extended functionality.
  • Open-source project under the Agentic AI Foundation (AAIF) at the Linux Foundation.

Related

  • Project
    limecloud/lime

    An open-source full-stack desktop AI agent that integrates coding, terminal operations, and multimodal research into a single visual workspace to execute complex tasks.

  • Project
    ultraworkers/claw-code

    A Rust-based CLI agent harness that allows users to run AI coding agents locally with support for multiple LLM providers.

  • Project
    Dicklesworthstone/pi_agent_rust

    A native Rust-based AI coding agent CLI that provides a high-performance, secure, and lightweight alternative to runtime-dependent AI assistants.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser workflows through a dedicated runtime engine.