Skip to main content
Goose is available in two forms: a command-line interface (CLI) for terminal users and a desktop application for those who prefer a graphical interface.

​
CLI Installation

The CLI is the fastest way to get started with goose and provides the full feature set.

​
Quick Install

curl -fsSL https://github.com/block/goose/raw/main/download_cli.sh | bash
The install scripts will download the appropriate binary for your system architecture and place it in your PATH. On first run, goose will guide you through provider configuration.

​
Install from Source (Cargo)

If you have Rust installed, you can build and install from source: 
cargo install goose-cli
This will compile goose locally and install the binary to ~/.cargo/bin/.

​
Manual Installation

1

Download the binary

Visit the GitHub releases page and download the appropriate archive for your platform:
  • macOS (ARM): goose-aarch64-apple-darwin.tar.gz
  • macOS (Intel): goose-x86_64-apple-darwin.tar.gz
  • Linux: goose-x86_64-unknown-linux-gnu.tar.gz
  • Windows: goose-x86_64-pc-windows-msvc.zip
2

Extract the archive

tar -xzf goose-*.tar.gz
3

Move to your PATH

sudo mv goose /usr/local/bin/
# Or to install without sudo:
mkdir -p ~/.local/bin
mv goose ~/.local/bin/
export PATH="$HOME/.local/bin:$PATH"
4

Verify installation

goose --version
You should see the version number printed to the console.

​
Desktop Application

The desktop app provides a rich graphical interface with session management, extension configuration, and visual feedback.

​
Download

Visit the GitHub releases page and download the installer for your platform:
  • macOS: goose-<version>.dmg
  • Windows: goose-<version>.msi or goose-<version>.exe
  • Linux: goose-<version>.AppImage or goose-<version>.deb

​
Install

  1. Open the .dmg file
  2. Drag the goose app to your Applications folder
  3. Open goose from Applications (you may need to allow the app in System Preferences > Security & Privacy)

​
First Launch

On first launch, the desktop app will guide you through:
  1. Selecting your LLM provider
  2. Entering API credentials
  3. Configuring optional extensions
You can modify these settings later in the app’s settings panel.

​
Platform-Specific Notes

​
macOS

On macOS, you may see a security warning when first running goose. To allow the app:
  1. Go to System Preferences > Security & Privacy
  2. Click “Open Anyway” next to the goose message
  3. Alternatively, right-click the app and select “Open”

​
Linux (WSL)

For Windows Subsystem for Linux (WSL) users: 
sudo apt update
sudo apt install build-essential libxcb1-dev
These packages are required for certain dependencies.

​
Windows

Windows users may need to install the Visual C++ Redistributable if not already present.

​
Verifying Installation

​
CLI

After installation, verify the CLI is working: 
goose --version
goose --help
You should see version information and a list of available commands.

​
Desktop App

Launch the desktop app and verify you can:
  1. Open the settings panel
  2. See available providers
  3. Create a new session

​
Next Steps

Now that goose is installed, configure your LLM provider:

Configuration Guide

Set up your LLM provider and customize goose’s behavior
Or jump straight to running your first session:

Quickstart

Run your first AI agent session in minutes

​
Troubleshooting

If you encounter issues during installation:
The goose binary is not in your PATH. Add the installation directory to your PATH:
# Add to ~/.bashrc or ~/.zshrc
export PATH="$HOME/.local/bin:$PATH"
Then restart your terminal or run source ~/.bashrc.
The binary may not be executable:
chmod +x /usr/local/bin/goose
# Or wherever you installed it
Try these steps:
  1. Check that you downloaded the correct version for your platform
  2. On macOS, allow the app in Security & Privacy settings
  3. On Linux, ensure you’ve made the AppImage executable: chmod +x goose-*.AppImage
  4. Check the logs in the diagnostics for error messages
For more troubleshooting help, see the Troubleshooting guide or join our Discord community.

Build docs developers (and LLMs) love

Get started for freeTalk to us