Goose

Goose

Open Source(Apache-2.0)
Verified
AI-Native

Now stewarded by Agentic AI Foundation (2025) — donated for open governance, still available.

Most customizable

Your open-source AI agent — desktop, CLI & API

Instant deletion
Works offline
IDE plugin
Global
Self-hostable
+9
Autonomous
Last updated: Oct 13, 2026
Compiled and verified by Intelloro · Ref INT-G2BNV5
Open Source
Visit Site53.0k
More
goose-docs.ai

Quick Answer

Goose is a general-purpose open source AI agent that runs on your own machine as a native desktop app, a full CLI, or an embeddable API. It connects to more than 70 extensions over the Model Context Protocol and works with 15+ model providers, including existing Claude, ChatGPT or Gemini subscriptions. Beyond code it is used for research, writing, automation and data analysis. It is Apache 2.0 licensed and governed by the Linux Foundation's Agentic AI Foundation.

About Goose

goose is a native open-source AI agent (Apache 2.0) that runs on your machine as a desktop app, CLI and API, for code, research, writing, automation and data analysis. It works with 15+ providers, including Anthropic, OpenAI, Google and Ollama, and connects to 70+ extensions through the Model Context Protocol. goose is part of the Agentic AI Foundation at the Linux Foundation.

AI-extracted from public sources. May contain errors. Methodology · Report an error
What Makes Goose Unique

goose works with any LLM, including existing Claude, ChatGPT or Gemini subscriptions via ACP, captures workflows as portable YAML recipes that can run in CI, and spawns subagents to handle tasks in parallel.

Decision Intelligence

Best For

Developers who want an open-source AI agent that runs on their own machine
Teams sharing repeatable workflows as recipes, including in CI
Users who want to use any LLM provider or their existing AI subscriptions
Pricing Overview

Type

Open Source

Starting Price

$0/mo

Free Trial

No

Credit Card

Not Required

Free Plan

Yes

Dimension Scores

· 4.3 avg

How good it is, across universal quality axes

Ease of Use2/10
Customization5/10
Support7/10
Integration2/10
Compliance & Data Protection2/10
Performance5/10
Planning Quality7/10
AI-scored from up to 37 public sources, reviewed by a person·High confidenceHow we score

Task Scores

· 6.0 avg

What it can do, per category it works in · showing 8 of 10 tasks scoring 5+

Action Library8/10
Multi Step Chains8/10
Autonomous Execution8/10
Workflow Building7/10
Api Connectivity7/10
Monitoring Logging6/10
Error Handling5/10
Conditional Logic5/10

Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →

Capabilities
Code
Automation
Agent
Categories
Code Assistant
Automation Agents
Developer Platform
Orchestration Agents
Limitations
  • -Requires your own LLM access — an API key or an existing Claude, ChatGPT or Gemini subscription
  • -Workflows are captured as YAML recipe files rather than built in a visual editor
Integrations & Connections
1 connection
Fit Score

Complexity

Advanced

Company Size

Solo
Small

Team Size

Individual
Small Team

Skill Level

Expert
Features
Desktop app, CLI and API
70+ MCP extensions
15+ LLM providers
Recipes as portable YAML workflows
Subagents for parallel tasks
MCP Apps with interactive UIs
Prompt injection detection and sandbox mode
ACP server for Zed, JetBrains and VS Code
Technical Capabilities
SDK Available
MCP Compatible
Multi-Agent
Human-in-Loop
Team Features
Webhook Support (unknown)
Has Demo
Function Calling
Sandbox Mode (unknown)
Audit Logs
No Signup
Works Offline
Requires Host App
Framework
MCP Server
Digital Employee

Deployment

Self Hosted
IDE Plugins
A2A Protocol:
MCP
HITL mode:
Approve
Compliance, Privacy & Trust
GDPR: No info available
SOC 2: No info available
HIPAA: No info available
Trains on user data: Unknown
Data retention: Unknown
Data deletion: Instant
Human review:
Recommended
Tech Specs
Response time (est.):
Moderate
MCP Servers:
GitHub
Context7
Fetch
Figma
Asana
Firecrawl
Exa
Chrome DevTools
Browserbase
Apify

The Model(s) Behind It

Model details — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

Training Data Provenance
Not disclosed
Relevant to EU AI Act Art. 53 / Annex XI (GPAI)
Supported Tools
Code Interpreter
Terminal
File System
Pricing Plans
Free
Free

    Looking for more Goose alternatives?

    Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.

    View All Alternatives

    User Reviews

    No reviews yet. Be the first to review!

    Platform, Content & Languages
    1 content types
    1 languages
    CodeEnglish+3 more

    Content Types

    Code

    Accepts

    Code

    Produces

    Code
    Text
    Languages: English

    Frequently Asked Questions

    What can Goose do?

    Goose can: Desktop app, CLI and API, 70+ MCP extensions, 15+ LLM providers, Recipes as portable YAML workflows. Best for: Developers who want an open-source AI agent that runs on their own machine.

    How much does Goose cost?

    Goose is open source and free to self-host. Cloud hosting options may have separate pricing.

    Is Goose free?

    Yes, Goose is open source and free to self-host. Managed hosting may carry separate costs.

    What makes Goose unique?

    goose works with any LLM, including existing Claude, ChatGPT or Gemini subscriptions via ACP, captures workflows as portable YAML recipes that can run in CI, and spawns subagents to handle tasks in parallel.

    What platforms does Goose support?

    Goose is available on desktop, CLI, API, and mobile.

    What languages does Goose support?

    Goose supports English.

    Does Goose work offline?

    Yes, Goose supports offline use — you can run it without an active internet connection.

    Who is Goose for?

    Goose is designed for Developers who want an open-source AI agent that runs on their own machine; Teams sharing repeatable workflows as recipes, including in CI; Users who want to use any LLM provider or their existing AI subscriptions.

    Video

    Trust Score

    60/100

    Good

    Based on 8 data signals

    Evidence: 5 of 12 expected facts verified · highest possible score 60

    Evidence strength: Strong

    Reflects publicly available data, not an independent audit

    Compliance & Verified38/38
    VerifiedYes
    Open-source licenseApache-2.0
    Human ReviewYes
    Human-in-the-loopYes
    HITL TypeYes
    Reliability0/10

    No published data

    Company17/17
    Company ListedYes
    Team Size5000+
    User Base10K-100K
    Health—

    Not yet checked

    AI Governance & Regulatory Disclosures

    Legally-sensitive fields — extracted from public vendor sources by our pipeline (AI extraction plus a source check) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.

    EU AI Act Risk Tier
    Unclassified

    Switching & Migration

    Migration Difficulty
    Moderate Effort
    Data portable as:
    JSON
    Support:
    Discord
    Quick Stats
    Agent TypeAutonomous
    MemoryLong Term
    PlanningAdvanced
    PlatformsDesktop, CLI, API +1
    User Base10K-100K
    Launched2025
    VerifiedOct 2026
    Company & Links
    Company NameAgentic AI Foundation
    Based inUnited States
    Last major updateJun 2026
    DocumentationChangelog

      We value your privacy

      We use cookies to enhance your browsing experience, analyze site traffic, and personalize content. Privacy Policy•Cookie Policy