# AI use cases for Goose (aaif-goose/goose) Repo: [aaif-goose/goose](https://github.com/aaif-goose/goose) | Use cases: 3 | Page: https://dedupedai.com/use-cases/aaif-goose-goose/ goose is a general-purpose, open-source AI agent that runs on your machine as a desktop app for macOS, Linux and Windows, a CLI and an API. It is built in Rust, works with 15+ providers including Anthropic, OpenAI, Google, Ollama and OpenRouter (or your existing Claude, ChatGPT or Gemini subscriptions via ACP), connects to 70+ extensions through the Model Context Protocol, and is part of the Agentic AI Foundation at the Linux Foundation. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Install the Goose CLI and hand it a real task: https://dedupedai.com/use-cases/aaif-goose-goose/install-goose-cli-and-run-a-task/ - Use Goose with your existing Claude, ChatGPT or Gemini subscription: https://dedupedai.com/use-cases/aaif-goose-goose/use-goose-with-your-existing-subscription/ - Extend Goose with MCP extensions for research and automation: https://dedupedai.com/use-cases/aaif-goose-goose/connect-goose-to-mcp-extensions/ ## How to install the Goose CLI and hand it a real task with Goose Repo: [aaif-goose/goose](https://github.com/aaif-goose/goose) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Install Goose from the terminal, connect a provider and let it work on code or a workflow. **Who it is for:** A developer who wants a local agent that is not tied to one editor or vendor. **The problem:** Most agents lock you into one provider or one IDE. **The outcome:** Goose running on your machine with your chosen provider, completing a task from the terminal. ### Steps 1. Install the CLI with `curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash` 2. Follow the Quickstart to configure a provider such as Anthropic, OpenAI or Ollama 3. Start a session in your project folder 4. Describe a task such as writing a script or migrating code 5. Review and approve its changes ### Prompt to paste into your agent ```text Install aaif-goose/goose CLI, configure it with , and in have it . Show me each command it runs and the final diff. ``` ### Caveat Risk, remote script: The CLI install pipes download_cli.sh from the GitHub release into bash; read it first if you prefer. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aaif-goose-goose/install-goose-cli-and-run-a-task/ ## How to use Goose with your existing Claude, ChatGPT or Gemini subscription with Goose Repo: [aaif-goose/goose](https://github.com/aaif-goose/goose) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Connect Goose to a subscription you already pay for through ACP instead of buying API credits. **Who it is for:** Someone with a Claude, ChatGPT or Gemini plan who does not want separate API billing. **The problem:** Agents usually need pay-per-token API keys on top of the subscription you already have. **The outcome:** Goose using your existing subscription through ACP providers. ### Steps 1. Download the desktop app or install the CLI 2. Open the ACP providers guide linked in the README 3. Connect your Claude, ChatGPT or Gemini subscription 4. Run a test task to confirm the provider works 5. Switch providers later without changing your workflow ### Prompt to paste into your agent ```text Help me connect aaif-goose/goose to my subscription using ACP following the docs, then run a small research task to confirm it works. ``` ### Caveat Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aaif-goose-goose/use-goose-with-your-existing-subscription/ ## How to extend Goose with MCP extensions for research and automation with Goose Repo: [aaif-goose/goose](https://github.com/aaif-goose/goose) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Add extensions from the 70+ available through the Model Context Protocol to let Goose use more tools. **Who it is for:** A knowledge worker who wants an agent that can search, read files and automate tasks beyond code. **The problem:** A bare agent cannot reach your tools, documents or services. **The outcome:** Goose with MCP extensions enabled, handling research, writing or data analysis tasks. ### Steps 1. Install the desktop app for macOS, Linux or Windows 2. Open extensions and pick the ones you need from the 70+ MCP extensions 3. Configure any credentials the extension requires 4. Give Goose a research or data analysis task that uses them 5. Use the Tutorials in the docs for more workflows ### Prompt to paste into your agent ```text Add the MCP extensions to aaif-goose/goose that I need for , configure them, and run the task end to end, listing which extension did what. ``` ### Caveat The README is short and points to the docs for setup details, so expect to follow the Quickstart and Tutorials. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/aaif-goose-goose/connect-goose-to-mcp-extensions/