Skip to main content
This domain is for sale. Contact Snagged to learn more.
GO

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.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 8 November 2026.

See pricing ↓

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

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

How it decides

What it decides by itself, and when it asks you

Mapped from the code in aaif-goose/goose.

In an ordinary goose session, plain code runs a fixed list of steps around the AI model's calls, and a plain text reply with no tool request ends the turn when nothing else is set up. A goal (/goal or /grind), a recipe's checks or required output, or a plugin's stop hook can each cause more work before the turn ends.

Read the full map: the judgments it shows and who holds each one
  • The model stopped; has it delivered the recipe's final output, or must it be told to?

    Decided by: Plain code

    Only for a recipe with a response schema: code looks since your kickoff message for a final-output call that succeeded. If there is one the turn may end; otherwise it adds a model-only message saying to call that tool now, and the agent continues.

  • If a review pass or check crashed or returned garbage, does the review say so?

    Decided by: Plain code

    On goose review's default path, a failed check or per-file pass adds no findings and a warning on stderr. If the review otherwise completes, it prints the findings that pass the severity floor and exits successfully.

  • When a subagent stops, did it complete, fail or get cancelled?

    Decided by: Plain code

    After reloading its session, code checks in a fixed order: a successful final-output call means Completed, even if the run was cancelled or errored afterwards; else a cancelled run is Cancelled; anything else is Failed.

  • Has the agent taken as many steps as it may without coming back to you?

    Decided by: Plain code

    When this step is reached, code counts the assistant turns kept since your kickoff message; at the budget it ends the turn with a fixed "Would you like me to continue?" message. In an ordinary session the budget is the session's max_turns, else GOOSE_MAX_TURNS, else 1000.

Three problems the map found

  1. The --max-tool-repetitions flag has no effect

    Already tracked

    goose's help says this flag limits consecutive identical tool calls. At this commit it does not: the command line accepts the value but never passes it to the repetition check, and the agent's standard setup gives that check no limit, so it never refuses a repeated call. goose's tracker has an open issue about how this limit should work, where contributors discuss wiring it up or removing it.

  2. By default, a failed review check still exits successfully

    No tracker issue found

    On goose review's default path, a check or per-file pass that fails, panics or returns output that cannot be parsed adds no findings and prints a warning on stderr. If the review otherwise completes it exits successfully, with nothing on stdout or in the exit status to mark the failed check.

  3. No code reads a verdict on a /goal

    No tracker issue found

    After /goal, goose says the agent will verify the goal before finishing. That check is left to the model: when code later clears the goal, it reads no verdict from the reply.

Read the full map

Not checked: This card was taken from the published map of goose at one commit and covers only decisions shown there; it did not look at code outside the map's scope (goose's core crates, command line, built-in extensions and desktop app) or at the 15 decisions left out of that edition, and no goose code was run to make it.

Mapped by agent-ops-patterns (open source) from aaif-goose/goose at commit cfb67d7. Mapped Nov 2, 2026. Last updated Nov 8, 2026.

Recent activity

What's happened with Goose lately

  • Score change
    Rubric upgrade v3_0 → v3.1: score 15/32 → 18/3615 → 18/36(+3)

    Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.

    See the news that prompted this

News mentions sourced from our news feed; score changes from periodic re-evaluations.

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.

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.

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: Nov 8, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Free / open source — full functionality available at no cost.
Details
AddedMarch 26, 2026
RefreshedNovember 9, 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 November 11, 2026
Free daily brief

When Goose changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

I use AI for: