Dev & Engineering general-purpose-agentclidesktopmcprust

goose

A general-purpose open source AI agent that goes beyond code — desktop, CLI, and API

FollowAgents review · FARS-2.0
Use with care
72/ 100 5-point scale 3.6 / 5
Trust16 / 25 · 3.2/5

Now governed under the Linux Foundation's Agentic AI Foundation (AAIF), offering more transparent governance than a single-company project; no isolated permission verification was performed for this review.

Reliability14 / 20 · 3.5/5

Has visible CI status badges and a health-score badge, suggesting mature engineering practice; no multi-task retest of a pinned version was performed.

Adaptability12 / 15 · 4.0/5

Positioned as a general-purpose agent, not limited to coding — also covers research, writing, automation, and data analysis, which broadens applicability but also makes a single verdict harder to generalize.

Convention13 / 15 · 4.3/5

Documentation site (goose-docs.ai) is well structured, offers a Custom Distributions mechanism, and publishes governance details (GOVERNANCE.md) openly.

Effectiveness12 / 15 · 4.0/5

50k+ stars, support for 15+ model providers, and 70+ MCP extensions indicate a mature ecosystem, but actual task effectiveness depends on the chosen model and enabled extensions — no unified benchmark exists.

Verifiability5 / 10 · 2.5/5

This review relied on the public README, governance docs, and repo metadata only — no independent install/reproduction was performed.

Evidence confidence:Low Reviewed Jul 24, 2026 Reviewed revision 85e8be250c2f
Before you use it
  • Actual risk depends heavily on which of the 70+ MCP extensions you enable — review each extension's permission scope individually
  • Supports many model providers; behavior and safety characteristics may differ across providers/models, and this review did not verify each one
  • This is a static review; no isolated dynamic verification was performed
Review evidence [1][2]
See the full review method →

What it does & when to use it

goose is a general-purpose AI agent that runs on your machine, useful for more than just coding — also research, writing, automation, and data analysis. It ships as a native desktop app (macOS/Linux/Windows), a full CLI, and an embeddable API, built in Rust for performance and portability. goose works with 15+ model providers (Anthropic, OpenAI, Google, Ollama, Bedrock, and more) and connects to 70+ extensions via the Model Context Protocol, and is now part of the Linux Foundation's Agentic AI Foundation (AAIF).

Executes tasks locally — install, execute, edit, test — and can use your existing Claude, ChatGPT, or Gemini subscription (via ACP) or a direct API key from any provider; connects to extensions through MCP for extra capabilities (e.g. accessing specific tools or services), and supports building custom distributions with preconfigured providers, extensions, and branding.

  1. Handle writing or research work beyond coding, from a local terminal or the desktop app
  2. Reuse an existing Claude/ChatGPT/Gemini subscription instead of buying separate API credits
  3. Automation scenarios that need MCP extensions to connect specific tools (databases, internal systems, etc.)
  4. Build a branded, preconfigured internal distribution on top of the same base

Pros & cons

Pros
  • General-purpose scope covers writing, research, and automation beyond coding
  • Governed under a Linux Foundation project, offering more transparent governance and longer-term maintenance assurance than a single-company project
  • Can reuse existing Claude/ChatGPT/Gemini subscription usage instead of forcing separate API billing
  • Supports 70+ MCP extensions and a custom-distribution mechanism suited to internal team redistribution
Limitations
  • General-purpose positioning means it may go less deep on any single scenario (e.g. pure coding) than a specialized tool
  • The real security boundary depends heavily on which extensions you enable, and needs per-extension review rather than a single overall judgment
  • This review did not verify actual runtime behavior under any specific combination of extensions

How to install

Download the desktop app from the official docs (goose-docs.ai's Getting Started page), or install the CLI directly: curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash.

How to use

After installing, launch the desktop app or run the CLI, configure a model provider (API key or existing subscription), optionally add MCP extensions, then describe your task in natural language, e.g. "Summarize this log file and produce a list of issues."

Compared to similar agents

Compared to coding-focused terminal agents like Codex CLI or opencode, goose's key differentiator is generality — it isn't limited to code tasks, and natively supports reusing a Claude/ChatGPT/Gemini subscription instead of forcing a separate API. If you need a local agent that spans more than just coding, or want to build an internally distributed variant on the same base, goose fits better.

FAQ

Is goose only for writing code?
No — it's positioned as a general-purpose agent, also supporting research, writing, automation, and data analysis alongside coding.
Can I use my existing ChatGPT/Claude subscription?
Yes, via ACP it can reuse an existing Claude, ChatGPT, or Gemini subscription, or you can configure a direct API key from any provider.
How are MCP extension permissions controlled?
goose doesn't uniformly enforce each extension's permission scope itself — review what each extension declares about its own permissions and data access before enabling it.

Related agents