Skip to main content
GO

Goose

A local, open source AI agent for engineering work

Goose is an on-machine AI agent that can automate development tasks from start to finish. It runs locally, works with any LLM, and connects to MCP servers or APIs for broader tool access.

Open Source
Android
Code Execution
B2B
CLI
Self-Hosted
On-Device / Edge
MCP Support
Visit Goose

Is this your tool? Claim this listing to manage your content and analytics.

Ask about Goose

Get answers based on Goose's actual documentation

Try asking:

About

What It Is

Goose is an open source AI agent for developers and engineering teams. It is built to do more than suggest code: according to its documentation, it can write and execute code, debug failures, orchestrate workflows, and interact with external APIs.

It runs locally on your machine and is available as both a desktop app and a CLI. Setup appears to center on following the quickstart and installation docs, then connecting your preferred LLM and any MCP servers or APIs you want it to use.

What to Know

Goose is notably more agentic than a typical coding assistant because it is designed to complete multi-step engineering tasks autonomously. The project also emphasizes flexibility: it supports any LLM and multi-model configuration, and it can be extended through MCP servers and APIs.

It is still a developer-focused tool, so it is not a general consumer assistant. The crawled content does not make pricing details explicit, and some setup specifics are left to the docs. Privacy-wise, the local runtime suggests you can keep execution on your machine, but model and integration behavior will depend on how you configure Goose and the providers you connect.

Key Features
Runs locally on the user's machine
Supports any LLM
Allows multi-model configuration
Connects to external MCP servers
Connects to external APIs
Use Cases
Automating software development tasks end to end
Debugging code and iterating on failed runs
Building prototypes or entire projects from scratch
Agenticness: Adaptive Collaborator 🤝

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Mar 27, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Adaptation
State & Memory
Safety

Categories

Pricing
  • Free: Open source under the Apache 2.0 license.
  • Pro: Not publicly available.
  • Enterprise: Not publicly available.
Details
AddedMarch 26, 2026
RefreshedMarch 28, 2026
Quick Facts
DeploymentOn-device / local
AutonomySemi-autonomous
Model supportSupports local models
Open sourceYes
MCP supportYes
Team supportSmall team
Pricing modelFree / open source
Interfacecli
Sources
Last updated March 30, 2026
Similar tools

Related Tools

Mintlify helps teams build and maintain product documentation with an AI-native workflow. It also adds an assistant for users and supports llms.txt and MCP for AI discovery.

Enterprise
B2B
For Developers
+4

ReadMe helps you build and maintain a developer hub with API docs, versioning, analytics, and built-in AI features. It’s aimed at teams that want docs that stay in sync with their product and API.

Paid
iOS
API
+4

GPT4All lets you run large language models on everyday desktops and laptops without API calls. It includes a desktop app and Python bindings for local inference, plus support for chatting with your own data.

Open Source
Desktop
B2B
+4

Amazon Q Developer helps you write, review, test, refactor, and upgrade code, with extra support for AWS operations and data/AI tasks. It runs in IDEs, the command line, AWS console, and chat tools like Slack and Microsoft Teams.

iOS
Code Execution
File Access
+4