01

What it does

goose · Local general-purpose open-source agent

Product and access

goose is part of the Agentic AI Foundation. Desktop, CLI and API use the local agent; models and connected services are selected separately.

Core features

6 features from provider sources · checked on 10 October 2026. Availability and limitations follow below.

  • Work locally across interfaces

    Desktop, CLI and API run the agent on your computer.

    Source 1
  • Connect MCP tools

    Extensions connect browsers, databases and other services through MCP.

    Source 1
  • Choose a model provider

    API providers, local models and compatible existing subscriptions can supply model access.

    Source 2
  • Reuse recipes

    YAML recipes capture instructions, extensions and parameters for repeatable workflows.

    Source 3
  • Load skills as context

    Agent Skills add reusable instructions and resources for specialised tasks.

    Source 4
  • Add tool-call review

    Adversary Mode evaluates configured tool calls against your rules before execution.

    Source 5
02

Does it fit my task?

Practical tasks

Editorial examples based on documented features. No product tests performed.

01

Prepare local data analysis

Your input
A data directory, a question and approved analysis tools.
Possible result
An analysis report with generated files and traceable commands.
What to check
Check selected files, calculations and the model and tool access used.
02

Save a repeatable workflow as a recipe

Your input
A proven workflow with inputs, extensions and output format.
Possible result
A parameterised recipe for later local runs.
What to check
Check parameters, permissions and results with a small sample dataset.
EDITORIAL EXAMPLE

A data directory, a question and approved analysis tools.

Your possible prompt

Read the project rules. Investigate [error], propose a small change, and run the relevant checks. Show me the diff and any remaining uncertainties.

Getting-started idea based on documented capabilities. Not an executed product test. Adapt the task, data, and permissions.

Requirements and limits

  • Requirement

    Set up model access and service costs

    The local agent requires configured model access. API usage, subscriptions and connected services have their own costs and limits.

    Source 2
  • Limitation

    ACP session restrictions

    With ACP providers, goose session resume and goose session fork currently do not support resuming or forking.

    Source 6
  • Limitation

    Adversary Mode fails open

    If the reviewer fails, the tool call is allowed. The mode reviews shell by default; additional tools must be explicitly included.

    Source 5
03

Can I use it?

Europe & regional availability

This source review covers the features and access options below. Other features may have different conditions.

Reviewed scope: Self-hosting; external services require separate checks
Reviewed on:

  • Depends on access and configuration

    Self-hosting and model access

    The project source describes running in your own environment and connecting models. Country requirements of chosen cloud models, tools and optional hosting services need additional checks. A complete Europe feature audit is still pending.

    Region, reason and source

    Region covered: EU/EEA, United Kingdom and Switzerland: to be checked separately

    Regulatory reason: not documented

    Official source · goose-docs.ai

Europe and regulation explained
04

Cost and effort

Prices and included usage

Pricing checked

goose is available under Apache 2.0. The software includes no fixed model quota; the selected provider determines ongoing costs.

PlanPriceIncluded
Open SourceUSD 0 software licence; ongoing

Desktop, CLI and API; requires your own model access and service accounts.

Price source

  • Model tokens, existing subscriptions or local compute are funded separately. No uniform monthly or per-run price is publicly specified.

Setup

Install goose, connect a model provider and configure extensions and tool permissions

05

Evidence and open questions

Open points

The reviewed sources contain no reliable information on these points. A gap says nothing about the product.

Not yet researched

  • Accounts & permissions
  • Operation & oversight

Sources and evidence

Official product documentation reviewed. Workflows and assessments are editorial; hands-on product tests are outside the scope of this directory.

Editorial team: Michael Meierhoff · sources reviewed on . Provider information is not independent evidence of performance.

Read profile as Markdown

How we assess the sources

Provider

Originally developed by Block, the project operates under the Agentic AI Foundation at the Linux Foundation.

Operator
Agentic AI Foundation
Organization
Open-source foundation
Provider sourcesSource 1 Source 2 Reviewed