Goose Docs

We're changing how people contribute to goose by moving design and discussion into issues before agents turn ready issues into code.

Benchmarks are most useful when they become bug reports. Here's how the goose team uses Terminal-bench failures, Harbor, and human judgment to improve real agent behavior.

goose now supports lifecycle hooks. Drop a plugin into a directory on disk and goose will run your shell scripts when things happen during a session: a tool is about to fire, a tool just finished, the user submitted a prompt, the session started, the sess

A lot of people prompt their agents one task at a time - "do this, now do that, now do the next thing." It works, but it's slow. Many people also want their agents doing many things at once: researching while coding, reviewing while testing, writing docs

Quick highlight: Sentient AGI recently shared with us some results with a challenge called "Grounded Reasoning" where teams tackled the Databricks OfficeQA benchmark using the MiniMax (2.5) open model. Highlights from the linked article: Using goose with

Most AI agents live in the terminal. They can read files, run commands, and write code - but ask them to click a button in a web app or fill out a form, and they're stuck. They can't see what's on screen, and they certainly can't interact with it. With v1

You can now run local models with goose directly on your machine. No Ollama, no Docker, no external server - just entirely within goose. We shipped built-in local inference powered by llama.cpp, and it's already available today in the desktop app. This is

Quick note: Mesh LLM is now in goose as an option for accessing and sharing (open) LLMs with friends and family. It uses the same llama.cpp infra as local mode to run models, with a twist. What is Mesh LLM? Mesh LLM is an associated project we're trying o

The biggest shift in developer tooling over the last year wasn't the rise of agents. It was the rise of agent subscriptions. We stopped choosing LLM platforms and counting tokens. We started choosing an agent CLI and paying a flat monthly fee. That works

goose started life in the terminal. The earliest versions were a Python CLI that ran the agent in-process - you typed a message, the model responded, tools executed, and everything happened in a single loop. That simplicity was a strength: it meant anyone