Skip to main content

Introducing codename goose

· 3 min read
Adewale Abati
Adewale Abati
Staff Developer Advocate

Introducing codename goose

We are thrilled to announce codename goose, your on-machine, open source AI agent built to automate your tasks.

Powered by your choice of large language models (LLMs), a user-friendly desktop interface and CLI, and extensions that integrate with your existing tools and applications, Goose is designed to enhance your productivity and workflow.

You can think of Goose as an assistant that is ready to take your instructions, and do the work for you.

While Goose's first use cases are engineering focused, the community has been exploring other non-engineering use cases for Goose as well. And it goes without saying, Goose is open source 🎉.

How Goose Works​

Goose operates as an intelligent, autonomous agent capable of handling complex tasks through a well-orchestrated coordination of its core features:

  • Using Extensions: Extensions are key to Goose’s adaptability, providing you the ability to connect with applications and tools that you already use. Whether it’s connecting to GitHub, accessing Google Drive or integrating with JetBrains IDEs, the possibilities are extensive. Some of these extensions have been curated in the extensions directory. Goose extensions are built on the Model Context Protocol (MCP) - enabling you to build or bring your own custom integrations to Goose.

  • LLM Providers: Goose is compatible with a wide range of LLM providers, allowing you to choose and integrate your preferred model.

  • CLI and Desktop Support: You can run Goose as a desktop app or through the command-line interface (CLI) using the same configurations across both.

Goose in Action​

Goose is able to handle a wide range of tasks, from simple to complex, across various engineering domains. Here are some examples of tasks that Goose has helped people with:

  • Conduct code migrations such as Ember to React, Ruby to Kotlin, Prefect-1 to Prefect-2 etc.
  • Dive into a new project in an unfamiliar coding language
  • Transition a code-base from field-based injection to constructor-based injection in a dependency injection framework.
  • Conduct performance benchmarks for a build command using a build automation tool
  • Increasing code coverage above a specific threshold
  • Scaffolding an API for data retention
  • Creating Datadog monitors
  • Removing or adding feature flags etc.
  • Generating unit tests for a feature

Getting Started​

You can get started using Goose right away! Check out our Quickstart.

Join the Goose Community​

Excited for upcoming features and events? Be sure to connect with us!