mistral-vibe

github.com · CLI Tool · Terminal

mistral-vibe is a CLI tool that runs in the terminal: Mistral AI's vibe coding tool. Its repository mistralai/mistral-vibe carries 5,079 stars and 12 contributors, and is licensed Apache-2.0. The latest stable release is v2.26.0, published 6 Oct 2026 with binaries for linux, macos, windows. The VS Code Marketplace reports 42,329 installs of mistralai.mistral-vibe-code. Vibe asks you to trust a directory before it runs there, and remembers the answer in `~/.vibe/trusted_folders.toml`.

Stars: 5,079; Verified 8 Oct 2026
Last commit: 6 Oct 2026; 2 days old when we read it; Verified 8 Oct 2026
License: Apache-2.0; Verified 8 Oct 2026
Latest stable release: v2.26.0; published 6 Oct 2026; Verified 8 Oct 2026
Contributors: 12; Verified 8 Oct 2026
PyPI downloads: 613,081 a week; mistral-vibe; Verified 8 Oct 2026
Homebrew installs: 146 in 30 days; mistral-vibe; Verified 8 Oct 2026
VS Code installs: 42,329; mistralai.mistral-vibe-code; Verified 8 Oct 2026
Repository: mistralai/mistral-vibe; Python; Verified 8 Oct 2026
Release binaries: linux, macos, windows; Verified 8 Oct 2026

Visit mistral-vibe mistralai/mistral-vibe on GitHub mistral-vibe alternatives

What mistral-vibe is

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

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

Use mistral-vibe when

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

Not the right fit for

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 is bad at

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

Security and data handling

Vibe asks you to trust a directory before it runs there, and remembers the answer in `~/.vibe/trusted_folders.toml`.

“Vibe includes a trust folder system to ensure you only run the agent in directories you trust.”

github.com/mistralai/mistral-vibe

Technical details

Category: CLI Tool · Terminal
Repository: mistralai/mistral-vibe
Default branch: main
Primary language: Python
Repository created: 8 Dec 2025
Newest commit on the default branch: 6 Oct 2026
Package formats: tar.gz, zip
Architectures: arm64, x64
Registries checked: npm:mistral-vibe, pypi:mistral-vibe, homebrew:mistral-vibe, vscode_marketplace:search(mistral-vibe)
Website check: https://github.com/mistralai/mistral-vibe answered HTTP 200

Alternatives to mistral-vibe

Claude CodeCommand-line AI coding agent that understands your codebase and automates tasks via natural languageCompare
AiderAI pair programming in your terminal with clean commitsCompare
Codex CLIOpenAI's lightweight terminal chat interface for code operationsCompare
GooseLocal on-machine AI agent that allows any LLM and MCP servers as extensionsCompare
MyCoder.aiOpen source AI coding assistant with Git/GitHub integration and parallel executionCompare

All mistral-vibe alternatives, ranked →

How we check this page

Machine facts. Stars, licence, the newest commit on the default branch, the latest stable release and download counts are read straight from the GitHub API and from npm, PyPI, Homebrew and the VS Code Marketplace. Each one shows the day it was last confirmed, not the day this page was built. A failed fetch keeps the old value and its old date rather than overwriting it.
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. If there is no link, we did not write the claim.
What we do not publish. No score out of five and no star rating. Every other claim here traces to a source, and a number we could not justify would undermine the ones that can.
This tool. Every claim carries the URL it came from and a verbatim quote from that URL, read on 2026-08-19.