Goose

Goose — Block's Apache-2.0 agent, MCP-native from the start, as both a CLI and a desktop app. Goose was built around MCP before most of the roster supported it — extensions are MCP servers, so the tool surface is the ecosystem rather than a plugin API. It ships as a CLI and a desktop app, is fully provider-agnostic including local models, and supports recipes: shareable, parameterised task definitions. Permission modes range from chat-only to fully automatic. Corporate backing from Block gives it more longevity than most independent open-source harnesses. Built by Block. Founded 2025. Open source under Apache-2.0.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Subagents — Yes, which only 5 of 14 tools here manage.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• Checkpoint & undo — No. Claude Code records Yes.
• Opens PRs — No. Claude Code records Yes.
• GitHub stars — 20,000, 7th of 9. Gemini CLI records 75,000.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 24 of 26 tracked fields carry a value for Goose, and 4 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. Goose is ahead on MCP (Yes against No) and Subagents (Yes against No). Aider takes Checkpoint & undo (Yes against No) and Repo indexing (AST / LSP repo map against agentic grep). That pattern repeats across the rest of the roster — see Goose alternatives for the other rivals, each compared the same way.

Company

Block

Founded

2025

Licence

Apache-2.0 (open source)

Fields we track

24 of 26

Last verified

2026-01-15

The most MCP-committed harness on the page — if your organisation has already built internal MCP servers, Goose turns them into an agent's toolset with no glue. Block's backing makes it a safer open-source bet than most, but it stops at your working tree.

Subagents

●Yes1st of 14

Community-reported

Checkpoint & undo

○No14th of 16

Inferred

Opens PRs

○No10th of 16

Inferred

Permissions

allowlist + OS sandbox1st of 16

Community-reported

BYOK

●Yes1st of 16

Inferredverified 2026-01-15

Headless / CI

●Yes1st of 16

Inferredverified 2026-01-15

MCP

●Yes1st of 15

Inferredverified 2026-01-15

Entry price

$0 /seat/mo1st of 16

Inferredverified 2026-01-15

Goose is the right call in these situations, each one drawn from a field we actually record:

• Organisations with an existing fleet of internal MCP servers.
• Recipes: parameterised, shareable tasks run non-interactively.
• Teams wanting an Apache-2.0 agent with a desktop app for non-terminal users.
• Subagents is your binding constraint. Goose records Yes, which only 5 of the 14 tools in the Coding agents roster do. We define that field as can the agent spawn child agents with their own context window and toolset, and collect their results? The main lever for keeping long tasks inside a context budget.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• Checkpoint & undo. Goose records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Opens PRs. Goose records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• GitHub stars. Goose records 20,000, 7th of 9 in the Coding agents roster. Gemini CLI records 75,000 on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 2 of the 26 fields we track for Goose are still blank: Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.