Open-source local agent

How to use
goose.

Running local coding and knowledge-work agents with selectable model providers, extensible MCP tools, reusable recipes, and configurable security controls.

Open goose ↗ Official download ↗
What it isopen-source general-purpose AI agent for desktop, terminal, and API workflows Workflows2 UpdatedJuly 2026

goose is a open-source general-purpose AI agent for desktop, terminal, and API workflows. Running local coding and knowledge-work agents with selectable model providers, extensible MCP tools, reusable recipes, and configurable security controls. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to goose

Get into the official goose experience with the right account and a setup you understand.

  1. 01

    Start at https://block.github.io/goose/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: goose is available as a desktop app, CLI, and API for macOS, Linux, and Windows, with multiple model providers, MCP extensions, skills, recipes, and subagents.

  3. 03

    A supported local system, the official app or CLI, a configured model provider, and explicit approval for every extension, credential, directory, and external service used.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful goose session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Install the official desktop app or CLI and select an approved model provider.

  2. 02

    Start in a dedicated workspace with only the files and credentials needed for one bounded task.

  3. 03

    Enable the minimum extensions and ask goose to inspect, plan, and identify risky actions before execution.

  4. 04

    Review tool calls, outputs, file changes, costs, and tests before accepting or sharing the result.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of goose output

Establish that an autonomous run did the right thing, not merely that it finished.

  1. 01

    Define what the run should achieve and what it must never touch before granting it a single tool.

  2. 02

    Read the full execution trace: which tools were called, with what arguments, and in what order.

  3. 03

    Verify the side effects directly in the target system rather than trusting the agent's own report of success.

  4. 04

    Confirm failures surfaced as failures — a silent retry loop or a swallowed error is more dangerous than a crash.

  5. 05

    Re-run the same task and compare: an agent that behaves differently across identical runs is not yet production-ready.

  • Verify side effects in the system of record, not in the agent's summary.
  • Require human approval for any irreversible or outward-facing action.
  • Log every tool call so a run can be reconstructed afterwards.
04

Privacy & permissions

Use goose safely

Bound what an autonomous system can reach before you let it run unattended.

  1. 01

    Enumerate every tool, credential, and system the agent can reach, and remove the ones it does not need.

  2. 02

    Require explicit human approval for irreversible actions: sending, publishing, paying, deleting, or deploying.

  3. 03

    Run against non-production data until behaviour is predictable across repeated runs.

  4. 04

    Set hard limits on spend, iterations, and runtime so a failure loop cannot run unbounded.

  5. 05

    Treat anything the agent reads from the web or a document as data, never as instructions it may follow.

  • A local agent can still expose data or damage files through model requests, shell access, extensions, browsers, and remote APIs. Use sandbox and permission controls, distrust instructions embedded in files or web pages, install extensions and skills only from reviewed sources, scope credentials and directories narrowly, pin reusable recipes, require approval for side effects, and verify all outputs and changes independently.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use goose for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

01 WorkflowComplete a local agent task safely with goose

Run a bounded coding or knowledge-work task with deliberate workspace, provider, extension, and permission choices.

 02 WorkflowTurn a goose workflow into a governed recipe

Capture a repeatable agent process as versioned YAML with explicit parameters, extensions, checks, and safe failure behavior.

06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →