Mistral Vibe Guide

Mistral’s coding agent for terminal sessions, scripts and configurable local or hosted models.

Last verified: 2026-09-22 · How we verify

Coding agentMistral AImacOSWindowsLinux

Suitable workflows

Developers choosing Mistral models, compatible endpoints or local inference.

Local operation still needs a suitable model and hardware; displayed cost estimates are not spending caps.

Agent workflowCLI surfaceMCPSkillsBring your own keyLocal models

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

See official pricing

Hosted API usage or local inference costs. The cost of metered usage or an external agent can be separate from the subscription.

Mistral-hosted models, local models or an OpenAI-compatible endpoint.

Verified families: Mistral, Local.

Python 3.12+ for manual installation; uv works on macOS, Linux and Windows.

Installation command · Python / uv

uv tool install mistral-vibe

Open your project folder in a terminal, then run:

vibe --agent plan

Use the setup wizard to add a Mistral key, or configure your local/compatible model endpoint.

Select the agent and approval policy in config.toml; plan mode is a useful starting point.

Ask for a refactoring plan, inspect the affected files, then choose which edits to apply.

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

vibe --prompt "Summarize the project structure without modifying files."

An open-source agent that connects model providers, MCP tools and repeatable recipes.

Terminal pair programming with repository maps, editable file context and Git integration.

An open-source coding agent with a terminal UI and configurable model providers.

Open a small, familiar project and confirm that your essential language tooling works.
Give the agent one bounded change with an observable acceptance criterion.
Review the diff, run the project’s checks and compare the result with your current workflow.
Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.