Goose

Goose, originally released as codename goose, is an open-source, general-purpose AI agent that runs on your own machine. Created by Block's open-source team and now governed as a vendor-neutral project under the Agentic AI Foundation at the Linux Foundation, it is built in Rust and distributed under a permissive Apache license. Although its first and best-known use is software engineering, Goose is designed to take on broader work too, including research, writing, automation, and data analysis.

What sets Goose apart from a code-suggestion tool is that it acts. Given a high-level goal, it breaks the task into steps and carries them out: reading and writing files, running code and tests, installing dependencies, executing terminal commands, refining its own output, and calling external APIs, iterating until the job is done. Because it operates in your actual development environment rather than inside a chat window, it behaves like an autonomous teammate that can build, run, and fix a project end to end.

A defining design choice is that Goose runs locally, so your code and data stay on your machine, which matters for sensitive or proprietary work. You interact with it through a native desktop app for macOS, Linux, and Windows, a full command-line interface for terminal and scripting workflows, or an API for embedding it in your own tools.

Goose is model-agnostic, working with many providers, including Anthropic, OpenAI, Google, and local models through Ollama, so you can balance performance, cost, and privacy and avoid lock-in. Its extensibility comes from the Model Context Protocol, the open standard Goose helped pioneer, which lets the agent connect to the systems where data and tools live, from content repositories to business applications and development environments. It can discover new systems on the fly, and the community keeps expanding what it can do by building new integrations.

Because it is open source, anyone can extend Goose, build a custom interface, or ship their own preconfigured distribution. It appeals to developers and technical teams who want an autonomous, on-machine agent they fully control, with their own choice of model and complete ownership of their data.