A RetroSearch Logo

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Search Query:

Showing content from https://block.github.io/goose/docs/quickstart below:

Quickstart | codename goose

Goose in 5 minutes

Goose is an extensible open source AI agent that enhances your software development by automating coding tasks.

This quick tutorial will guide you through:

Let's begin 🚀

Install Goose​

Choose to install Goose on CLI and/or Desktop:

To download Goose Desktop for macOS, click one of the buttons below:

  1. Unzip the downloaded zip file.
  2. Run the executable file to launch the Goose Desktop application.

Run the following command to install Goose:

curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash

To download Goose Desktop for Linux, choose the buttons below:

For Debian/Ubuntu-based distributions:

  1. Download the DEB file
  2. Navigate to the directory where it is saved in a terminal
  3. Run sudo dpkg -i (filename).deb
  4. Launch Goose from the app menu

Run the following command to install the Goose CLI on Linux:

curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash

Choose to install Goose on CLI and/or Desktop:

To download Goose Desktop for Windows, click the button below:

  1. Unzip the downloaded zip file.
  2. Run the executable file to launch the Goose Desktop application.

Run the following command in Git Bash, MSYS2, or PowerShell to install the Goose CLI natively on Windows:

curl -fsSL https://github.com/block/goose/releases/download/stable/download_cli.sh | bash

Learn about prerequisites in the installation guide.

Configure Provider​

Goose works with supported LLM providers. When you install Goose, you'll be prompted to choose your preferred LLM and supply an API key.

Use the up and down arrow keys to navigate the CLI menu, and press Enter once you've selected a choice.

┌   goose-configure
│
◇ What would you like to configure?
│ Configure Providers
│
◇ Which model provider should we use?
│ Google Gemini
│
◇ Provider Google Gemini requires GOOGLE_API_KEY, please enter a value
│▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
│
◇ Enter a model from that provider:
│ gemini-2.0-flash-exp
│
◇ Hello! You're all set and ready to go, feel free to ask me anything!
│
└ Configuration saved successfully

Billing

Google Gemini

offers a free tier you can get started with. Otherwise, you'll need to ensure that you have credits available in your LLM Provider account to successfully make requests.

Some providers also have rate limits on API usage, which can affect your experience. Check out our Handling Rate Limits guide to learn how to efficiently manage these limits while using Goose.

Model Selection

Goose relies heavily on tool calling capabilities and currently works best with Anthropic's Claude 3.5 Sonnet and OpenAI's GPT-4o (2024-11-20) model.

Start Session​

Sessions are single, continuous conversations between you and Goose. Let's start one.

After choosing an LLM provider, you’ll see the session interface ready for use.

Type your questions, tasks, or instructions directly into the input field, and Goose will immediately get to work.

  1. Make an empty directory (e.g. goose-demo) and navigate to that directory from the terminal.
  2. To start a new session, run:

Goose Web

CLI users can also start a session in Goose Web, a web-based chat interface:

Write Prompt​

From the prompt, you can interact with Goose by typing your instructions exactly as you would speak to a developer.

Let's ask Goose to make a tic-tac-toe game!

create an interactive browser-based tic-tac-toe game in javascript where a player competes against a bot

Goose will create a plan and then get right to work on implementing it. Once done, your directory should contain a JavaScript file as well as an HTML page for playing.

Install an Extension​

While you're able to manually navigate to your working directory and open the HTML file in a browser, wouldn't it be better if Goose did that for you? Let's give Goose the ability to open a web browser by enabling the Computer Controller extension.

  1. Click the button in the top-left to open the sidebar.
  2. Click Extensions in the sidebar menu.
  3. Toggle the Computer Controller extension to enable it. This extension enables webscraping, file caching, and automations.
  4. Return to your session to continue.
  5. Now that Goose has browser capabilities, let's ask it to launch your game in a browser:
  1. End the current session by entering Ctrl+C so that you can return to the terminal's command prompt.
  2. Run the configuration command
  1. Choose Add extension > Built-in Extension > Computer Controller, and set timeout to 300s. This extension enables webscraping, file caching, and automations.
┌   goose-configure
│
◇  What would you like to configure?
│  Add Extension
│
◇  What type of extension would you like to add?
│  Built-in Extension
│
◇  Which built-in extension would you like to enable?
│  ○ Developer Tools
│  ● Computer Controller (controls for webscraping, file caching, and automations)
│  ○ Google Drive
│  ○ Memory
│  ○ JetBrains
│        
◇  Please set the timeout for this tool (in secs):
│  300
│
└  Enabled Computer Controller extension
  1. Now that Goose has browser capabilities, let's resume your last session:
  1. Ask Goose to launch your game in a browser:
open index.html in a browser

Go ahead and play your game, I know you want to 😂 ... good luck!

Next Steps​

Congrats, you've successfully used Goose to develop a web app! 🎉

Here are some ideas for next steps:

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4