Skip to main content
VibeFactory logoVibeFactory
Goose logo
mistral-vibe logo

Goose vs mistral-vibe

What the data says

Goose — 55,064 stars, committed 7 Oct 2026, Apache-2.0. mistral-vibe — 5,079 stars, committed 6 Oct 2026, Apache-2.0.

Goose is a CLI tool that runs in the terminal: Local on-machine AI agent that allows any LLM and MCP servers as extensions.

mistral-vibe is a CLI tool that runs in the terminal: Mistral AI's vibe coding tool.

Goose and mistral-vibe, fact by fact

FactGoosemistral-vibe
StarsGoose has 49,985 more stars (11×).55,064Verified 8 Oct 20265,079Verified 8 Oct 2026
Newest commitBoth committed on the same day.7 Oct 20260 days old when we read itVerified 8 Oct 20266 Oct 20262 days old when we read itVerified 8 Oct 2026
ContributorsGoose has 441 more contributors (38×).453Verified 8 Oct 202612Verified 8 Oct 2026
LicenseBoth ship under Apache-2.0.Apache-2.0Verified 8 Oct 2026Apache-2.0Verified 8 Oct 2026
Latest stable releasemistral-vibe released 3 days more recently.v1.53.0published 2 Oct 2026Verified 8 Oct 2026v2.26.0published 6 Oct 2026Verified 8 Oct 2026
PyPI downloadsnot tracked for Goose613,081 a weekmistral-vibeVerified 8 Oct 2026
Homebrew installsnot tracked for Goose146 in 30 daysmistral-vibeVerified 8 Oct 2026
VS Code installsnot tracked for Goose42,329mistralai.mistral-vibe-codeVerified 8 Oct 2026
Repositoryaaif-goose/gooseRustVerified 8 Oct 2026mistralai/mistral-vibePythonVerified 8 Oct 2026

What we know about Goose

goose is the only agent in this set governed by a foundation rather than a vendor, and it can borrow an existing Claude, ChatGPT or Gemini subscription over the Agent Client Protocol instead of an API key.

“goose is part of the [Agentic AI Foundation (AAIF)](https://aaif.io/) at the Linux Foundation.”

github.com/aaif-goose/goose

Automate work that is not coding — research, writing, data analysis — on the same machine and the same agent, through the desktop app, the CLI or the API.

“goose is a general-purpose AI agent that runs on your machine. Not just for code — use it for research, writing, automation, data analysis, or anything you need to get done.”

github.com/aaif-goose/goose

Wire the agent into tools you already run: goose connects to 70+ extensions over the Model Context Protocol.

“Connect to 70+ extensions via the [Model Context Protocol](https://modelcontextprotocol.io/) open standard.”

github.com/aaif-goose/goose

Ship one configuration to a whole team: a custom distribution bundles the providers, extensions and branding before anybody installs it.

“[Custom Distributions](https://github.com/aaif-goose/goose/blob/main/CUSTOM_DISTROS.md) — build your own goose distro with preconfigured providers, extensions, and branding”

github.com/aaif-goose/goose

Model choice is not free: goose leans on tool calling, so a weak or local model degrades it, and the vendor names Claude 4 as the model it works best with.

“goose relies heavily on tool calling capabilities and currently works best with Claude 4 models.”

goose-docs.ai/docs/getting-started

Two OpenAI reasoning models do not run at all, because they cannot call tools.

“o1-mini and o1-preview are not supported because goose uses tool calling.”

goose-docs.ai/docs/getting-started

Unattended scheduling is broken in 1.45.0: headless runs die at the first tool call and a recipe's own goose_mode is ignored.

“Scheduler unusable for unattended recipes on 1.45.0: headless runs die at first tool call, recipe-level goose_mode is silently ignored, an interrupted run-now permanently wedges the job, and spawned sessions get no schedule_id”

github.com/aaif-goose/goose

A developer who wants the widest model catalogue in a terminal should pick OpenCode, which reaches 75+ providers from one config file.

“OpenCode uses the AI SDK and Models.dev to support 75+ LLM providers and it supports running local models.”

opencode.ai/docs/providers

What Goose costs

goose charges nothing for itself; you pay whichever provider you configure, and it accepts a ChatGPT Plus or Pro subscription in place of an API key.

“Access GPT-5 Codex models optimized for code generation and understanding. Requires a ChatGPT Plus/Pro subscription.”

goose-docs.ai/docs/getting-started

Full Goose profile · Visit block.github.io

What we know about mistral-vibe

Mistral Vibe sets its risk level by picking one of four named agent profiles — ask, plan, accept-edits and auto-approve — rather than by editing a permission table, and accept-edits, which auto-approves edits but not shell commands, is the shipped default.

“- **`ask`**: Requires approval for tool executions. · - **`plan`**: Read-only agent for exploration and planning. Auto-approves safe tools like `grep` and `read`. · - **`accept-edits`**: The default agent. Auto-approves file edits only (`write_file`, `edit`). Useful for code refactoring. · - **`a…”

github.com/mistralai/mistral-vibe

Refactor with edits applied but shell commands still gated: that is the shipped default, the `accept-edits` agent.

“- **`accept-edits`**: The default agent. Auto-approves file edits only (`write_file`, `edit`). Useful for code refactoring.”

github.com/mistralai/mistral-vibe

Run two agent sessions on one repository at once: `--worktree` claims a fresh git worktree per session on a `vibe/<name>` branch, so the checkouts cannot collide.

“Unlike the named form, this never reuses an existing worktree: Vibe claims a free name, adding `-2`, `-3` and so on if needed, so two sessions started at once can never land in the same checkout. The branch is always `vibe/<name>`, matching the worktrees Le Chat Desktop creates.”

github.com/mistralai/mistral-vibe

Hand the agent a screenshot: `.png`, `.jpg`, `.jpeg`, `.gif` and `.webp` attach through `@` mentions as native multimodal content.

“- Image attachments via `@` mentions — `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp` files are sent to vision-capable models (e.g. Mistral Medium 3.5) as native multimodal content.”

github.com/mistralai/mistral-vibe

Windows is not a supported target, only a working one; Mistral tests and aims at UNIX.

“> [!WARNING] · > Mistral Vibe works on Windows, but we officially support and target UNIX environments.”

github.com/mistralai/mistral-vibe

There is no bring-your-own-provider path in the default setup: Vibe asks for a Mistral API key from console.mistral.ai and stores it in `~/.vibe/.env`.

“To use Vibe, you'll need a Mistral API key. You can obtain one by signing up at [https://console.mistral.ai](https://console.mistral.ai).”

github.com/mistralai/mistral-vibe

Interrupting the agent can break the turn: after an interrupt Vibe emits two user messages in a row, which the Devstral 2 template rejects, and the issue is open with 16 comments.

“bug: Mistral-Vibe produces multiple user messages in a row after interrupts, which the Devstral 2 template does not allow”

github.com/mistralai/mistral-vibe

A Windows-first team should pick Crush, whose built-in Bash interpreter makes the same config run on Windows as on Linux.

“Because Crush has a native, built-in Bash interpreter, Bash-based config works identically across all platforms, including Windows.”

github.com/charmbracelet/crush

What mistral-vibe costs

Mistral's Free plan includes Vibe with limited coding sessions and $10 a month of API credits.

“Limited coding sessions. · State-of-the-art image generation. · Test Mistral models in Studio. · $10 /mo in API credits.”

mistral.ai/pricing

The Pro plan is $14.99 a month, lifts the cap to all-day coding in the CLI, and carries $30 a month of API credits; Team is $24.99 per user per month.

“All-day coding in the CLI, IDE, or on web. · More image generations. · $30 /mo in API credits.”

mistral.ai/pricing

Full mistral-vibe profile · Visit github.com

Questions people ask

Are Goose and mistral-vibe still maintained?
Goose committed to aaif-goose/goose (main) on 7 Oct 2026. mistral-vibe committed to mistralai/mistral-vibe (main) on 6 Oct 2026. Both readings come from the default branch of each repository, on the date shown beside them.
What do Goose and mistral-vibe cost?
Goose: goose charges nothing for itself; you pay whichever provider you configure, and it accepts a ChatGPT Plus or Pro subscription in place of an API key. mistral-vibe: Mistral's Free plan includes Vibe with limited coding sessions and $10 a month of API credits. The Pro plan is $14.99 a month, lifts the cap to all-day coding in the CLI, and carries $30 a month of API credits; Team is $24.99 per user per month. Every figure here is quoted from the vendor's own page and linked beside the claim.
Is Goose or mistral-vibe open source?
Goose's repository aaif-goose/goose reports the Apache-2.0 licence. mistral-vibe's repository mistralai/mistral-vibe reports the Apache-2.0 licence. We read the licence GitHub reports for the repository, which is not the same question as whether the hosted product is free.

How we check this page

  • Machine facts. Stars, contributors, the newest commit on the default branch, the licence GitHub reports and the latest stable release come from the GitHub API, and download counts from npm, PyPI, Homebrew and the VS Code Marketplace. Each value carries the day it was last confirmed, never the day this page was built. The line under each label is arithmetic on those two values.
  • Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. Where there is no link, we wrote no claim.
  • Index status. Both Goose and mistral-vibe carry claims we read, quoted and linked. So this page is offered to search engines.

Related comparisons

Pairs we can answer for come first.

Profiles for the tools named here