Skip to main content
toolsSource-backedReview first Safety Privacy

Goose

Open-source, extensible AI agent that goes beyond code suggestions to install, execute, edit, and test with any LLM, available as a desktop app, CLI, and API with 70+ MCP extensions.

by Agentic AI Foundation·added 2026-06-05·
CLI
HarnessCLI
Review first review before installing

Open the source and read safety notes before installing.

Safety notes

  • Goose installs, executes, edits, and tests code and runs commands locally, so it can change files and system state on your machine.
  • It connects to 70+ MCP extensions; each extension adds capabilities and its own integration risk, so enable only those you trust.
  • Review actions and generated code before allowing changes to important repositories or systems.
  • Because it works across 15+ providers, confirm which provider and model a session uses before sending sensitive context.

Privacy notes

  • Your code and prompts are sent to whichever LLM provider you configure; data handling follows that provider's policies.
  • API keys and provider credentials should be stored securely and never committed to source control.
  • MCP extensions can access local files and external services depending on their scope; review what each extension can reach.

Prerequisites

  • An LLM provider API key, or an existing Claude, ChatGPT, or Gemini subscription via an ACP provider.
  • macOS, Linux, or Windows for the desktop app or CLI.
  • MCP-compatible extensions if you want to expand Goose beyond its built-in tools.

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Tool listing metadata
Pricing
open-source
Disclosure
editorial
Application category
DeveloperApplication
Operating system
macOS, Windows, Linux
Full copyable content
## Overview

Goose is an open-source, extensible AI agent that goes beyond code suggestions —
it installs, executes, edits, and tests with any LLM. It runs as a native
desktop app, a CLI, and an API, and is used for research, writing, automation,
data analysis, and code tasks.

It is released under the Apache-2.0 license and is primarily Rust. The project
moved from `block/goose` to the Agentic AI Foundation (AAIF) at the Linux
Foundation, and its current home is `aaif-goose/goose`.

## Features

- Works as a desktop app, CLI, and API.
- Provider flexibility across 15+ providers including Anthropic, OpenAI, Google,
  Ollama, OpenRouter, Azure, and Bedrock.
- Connects to 70+ extensions via the Model Context Protocol (MCP).
- ACP integration to use existing Claude, ChatGPT, or Gemini subscriptions.
- General-purpose automation beyond code generation.

## Use Cases

- Run a local AI agent that can execute and test changes, not just suggest them.
- Use your preferred provider or an existing subscription via ACP.
- Extend the agent with MCP extensions for tools and data sources.
- Automate research, writing, and data tasks alongside coding.

## Installation

Install the desktop app or CLI from the official installation guide at
[goose-docs.ai](https://goose-docs.ai/docs/getting-started/installation). Choose
your platform build and configure an LLM provider before first use.

## Disclosure

Editorial listing. No paid placement or affiliate relationship. Goose is open
source under Apache-2.0 and hosted by the Agentic AI Foundation; using it
requires your own LLM provider access.

About this resource

Overview

Goose is an open-source, extensible AI agent that goes beyond code suggestions — it installs, executes, edits, and tests with any LLM. It runs as a native desktop app, a CLI, and an API, and is used for research, writing, automation, data analysis, and code tasks.

It is released under the Apache-2.0 license and is primarily Rust. The project moved from block/goose to the Agentic AI Foundation (AAIF) at the Linux Foundation, and its current home is aaif-goose/goose.

Features

  • Works as a desktop app, CLI, and API.
  • Provider flexibility across 15+ providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, and Bedrock.
  • Connects to 70+ extensions via the Model Context Protocol (MCP).
  • ACP integration to use existing Claude, ChatGPT, or Gemini subscriptions.
  • General-purpose automation beyond code generation.

Use Cases

  • Run a local AI agent that can execute and test changes, not just suggest them.
  • Use your preferred provider or an existing subscription via ACP.
  • Extend the agent with MCP extensions for tools and data sources.
  • Automate research, writing, and data tasks alongside coding.

Installation

Install the desktop app or CLI from the official installation guide at goose-docs.ai. Choose your platform build and configure an LLM provider before first use.

Disclosure

Editorial listing. No paid placement or affiliate relationship. Goose is open source under Apache-2.0 and hosted by the Agentic AI Foundation; using it requires your own LLM provider access.

#ai-agent#cli#desktop-app#mcp#open-source#automation

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.