# Mistral Vibe Guide

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

Canonical URL: https://aiidelist.com/blog/traeide-mistral-vibe

Language: en

Published: 2026-10-03

Updated: 2026-10-03

> Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.

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

Coding agent · Mistral AI · macOS · Windows · Linux

 

## Suitable workflows

Developers choosing Mistral models, compatible endpoints or local inference.

## Limitations and billing

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

## Capabilities we verified

Agent workflow · CLI surface · MCP · Skills · Bring your own key · Local models

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

## Pricing & usage

**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.

## Models & access

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

Verified families: Mistral, Local.

<span id="cli-setup"></span>

## Install and start the CLI

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

```
uv tool install mistral-vibe
```

Open your project folder in a terminal, then run:

```
vibe --agent plan
```

## Account and authentication

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

## Project configuration and tools

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

## First task to try

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

## Script usage

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."
```

## Related CLI tools

[All AI CLI tools →](/blog/traeide-coding-agents)

[goose](/blog/traeide-goose) — An open-source agent that connects model providers, MCP tools and repeatable recipes.

[Aider](/blog/traeide-aider) — Terminal pair programming with repository maps, editable file context and Git integration.

[OpenCode](/blog/traeide-opencode) — An open-source coding agent with a terminal UI and configurable model providers.

## Project evaluation checklist

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

## Related TRAE guides

- [TRAE product overview](/ide/trae)
- [Trae IDE / TraeCode Download](/blog/traeide-download)
- [TraeCode Guide](/blog/traeide-traecode)
- [TraeWork Guide](/blog/traeide-traework)
- [TRAE Pricing: TraeCode & TraeWork](/blog/traeide-pricing)
- [TRAE Models & Model Access](/blog/traeide-models)
- [TraeWork vs TraeCode (Trae IDE)](/blog/traeide-traework-vs-traecode)
- [Trae MCP Setup & Troubleshooting](/blog/traeide-mcp)