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.
Is this your tool? Claim this listing to manage your content and analytics.
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 oneThe model stopped; has it delivered the recipe's final output, or must it be told to?
Decided by: Plain codeOnly 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 codeOn 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 codeAfter 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 codeWhen 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
The --max-tool-repetitions flag has no effect
Already trackedgoose'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.
By default, a failed review check still exits successfully
No tracker issue foundOn 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.
No code reads a verdict on a /goal
No tracker issue foundAfter /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.
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.
What's happened with Goose lately
- Score changeRubric 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
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.
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.
Proposes and executes multi-step plans with your approval.
Dimension Breakdown
Categories
Ask about Goose
Try asking:
- Free / open source — full functionality available at no cost.
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.