Mistral Vibe: Free & Open-Source AI Coding Assistant from Mistral AI

Mistral Vibe is an AI coding agent from Mistral AI for work tasks and coding tasks. It is available through the web app, a VS Code extension, and the mistral-vibe CLI. You can ask it to inspect a repository, edit files, run commands, and prepare code changes from a natural language request.

The product is no longer just a terminal coding assistant. Mistral Vibe now has three main surfaces: Chat for regular AI conversations, Work Mode for multi-step tasks across connected apps, and Code Mode for software engineering work in the terminal, IDE integrations, and remote coding sessions.

Key Features

• CLI coding assistant: Run vibe inside a project to inspect files, apply patches, run commands, and track tasks from the terminal.
• Code Mode: Start a coding session in Vibe’s web interface, connect a repository, inspect changes, and move the task toward a reviewable pull request.
• IDE support: Vibe works in editors and IDEs that support Agent Client Protocol. Mistral also includes Vibe for IDE in its coding feature set.
• Project-aware context: Vibe reads project structure, Git status, mentioned paths, trusted folders, extra directories, and local instructions before it works on a repository.
• File and terminal tools: The agent has read_file, write_file, search_replace, grep, bash, todo, ask_user_question, and task, with permissions controlling when they run.
• Built-in agents: The CLI ships with default, plan, accept-edits, and auto-approve profiles. Choose a profile with --agent or set a default for interactive sessions.
• Subagents: Vibe delegates work through the task tool. The built-in explore subagent is read-only and keeps codebase exploration out of the main session context.
• Interactive questions: The ask_user_question tool lets the agent stop mid-task and ask for a choice or a free-text answer before it continues.
• Skills and slash commands: Skills add reusable instructions, tools, slash commands, and specialized behavior. Vibe discovers them from project-level and user-level locations, including Agent Skills standard paths.
• MCP server support: You can configure Model Context Protocol (MCP) servers with http, streamable-http, or stdio transports, custom headers, API key environment variables, timeouts, and tool permissions.
• Session controls: Use --continue, --resume, --workdir, and --add-dir to continue work, resume a saved session, choose a working directory, or include additional directories.
• Safety controls: Tool approval, trusted folders, configurable permissions, and agent profiles separate read-only planning from edit-heavy sessions.

Mistral Vibe Pricing and Free Plan

Mistral Vibe is not an unlimited free coding agent. The Free plan is best for trying Vibe, using web and mobile access, working with Mistral models, running limited messages and searches, testing limited coding sessions, generating images, and trying connectors. It is a real entry point, but not a serious daily coding plan.

The Pro plan costs $14.99 per month, excluding taxes. It is the first plan Mistral positions for full Vibe access, long-running tasks, and all-day coding in the CLI, IDE, and web. It also raises limits for messages, web searches, harder tasks, image generations, and support.

The Team plan costs $24.99 per user per month, excluding taxes. It is built for shared workspaces and adds up to 30GB of storage per user, domain name verification, and data export. Enterprise is custom priced and covers private deployments, custom models, custom agents, custom workflows, audit logs, SAML SSO, and white-label options.

Verified students can get the Education plan at $5.99 per month, excluding taxes, with eligibility limits. For API usage, Mistral bills per million input and output tokens. The pricing page lists Devstral 2, the agentic coding model, at $0.40 per million input tokens and $2.00 per million output tokens. This API pricing is separate from the consumer plan framing and matters if you extend usage through pay-as-you-go credits or build directly on the API.

Use Cases

• Legacy system modernization: Ask the agent to refactor older code toward a newer architecture, then review the patch before you merge it.
• Cross-file bug fixes: Describe a bug that spans multiple files. The agent can search the repository, inspect related code, and propose a consistent fix.
• Dependency updates: Use the agent to find imports, update package references, and adjust code affected by changed APIs.
• Codebase exploration: Use the built-in plan agent or explore subagent to map an unfamiliar repository before you ask for edits.
• Automated documentation: Generate README updates, API notes, migration notes, or inline comments after the agent inspects the relevant files.
• Test generation: Ask Vibe Code to write unit or integration tests that match the patterns already used in the project.
• Repeatable engineering routines: Create skills for code review, release checks, security review, documentation, or repo-specific conventions.
• Work task automation: Use Work Mode for multi-step tasks such as gathering context from connected apps, analyzing structured data, drafting a report, or scheduling a recurring task.

How to Use Mistral Vibe CLI

Installation

One-line install for Linux and macOS:

curl -LsSf https://mistral.ai/vibe/install.sh | bash

Using uv:

uv tool install mistral-vibe

Using pip:

pip install mistral-vibe

Windows: Vibe works on Windows, but the project targets UNIX environments. Windows users should expect a less primary support path and should install uv before using the uv tool install mistral-vibe command.

Initial Setup

Navigate to your project root and run vibe. On first launch, the CLI creates ~/.vibe/config.toml, asks for a Mistral API key if one is not configured, and saves credentials to ~/.vibe/.env. You can also run vibe --setup for separate setup.

You can set the API key with MISTRAL_API_KEY or a ~/.vibe/.env file. Environment variables take precedence over values saved in the dotenv file. General settings belong in config.toml, not the .env file.

Interactive Mode

Run vibe to start the interactive chat loop. Use Ctrl+J or Shift+Enter for multi-line prompts, type @ to reference files with path autocompletion, and prefix a command with ! to run it directly in your shell.

You can press Ctrl+G to edit input in an external editor, Ctrl+O to toggle tool output, Ctrl+T to toggle the todo list, and Shift+Tab to cycle through available agents.

You can also start directly with a prompt:

vibe "Refactor the main function in cli/main.py to be more modular."

Trust Folder System

Vibe uses a trust folder system for directories that contain Vibe configuration. When you first run Vibe in a new directory with a .vibe subfolder, it may ask whether you trust that folder. Trusted folders are saved in ~/.vibe/trusted_folders.toml.

This matters because trusted directories can contribute local configuration, prompts, agents, skills, and instructions. Do not trust a repository if you have not inspected its local automation and configuration files.

Programmatic Mode

Use programmatic mode for scripts, repeatable checks, and non-interactive tasks:

vibe --prompt "Analyze the codebase" --max-turns 5 --max-price 1.0 --max-tokens 50000 --output json

Important options include --max-turns, --max-price, --max-tokens, --enabled-tools, and --output. Output can be text, json, or streaming. In the GitHub documentation, programmatic mode uses auto-approve by default, so you should restrict tools and cost limits before using it in automation.

Voice Mode

Voice mode is experimental. Use /voice to toggle dictation. Ctrl+R starts recording, any key stops recording, and Escape or Ctrl+C cancels recording.

Configuration

Vibe looks for ./.vibe/config.toml first and then falls back to ~/.vibe/config.toml. The configuration file controls the active model, default agent, tool permissions, skill paths, MCP servers, prompts, session behavior, update behavior, telemetry, notifications, and UI preferences.

You can set VIBE_HOME to store configuration, API keys, agents, prompts, tools, and logs in another directory. This helps keep work and personal coding environments separate.

AGENTS.md and Custom Prompts

Mistral Vibe supports AGENTS.md files for instructions. A user-level file at ~/.vibe/AGENTS.md applies across projects, while project-level files are loaded from the current directory up to the trust root. Closer directories override more distant instructions.

You can also replace the system prompt with a Markdown file in ~/.vibe/prompts/ or a project-local .vibe/prompts/ directory, then set system_prompt_id. For compaction, set compaction_prompt_id to control how long sessions are summarized.

Custom Agents and Tool Management

Create custom agent configurations in ~/.vibe/agents/ or a project-level agents directory. A custom agent can specify a model, prompt, disabled tools, and per-tool permission behavior. Use enabled_tools and disabled_tools with exact names, glob patterns, or re: regular expressions to control what the agent can use.

MCP Server Configuration

MCP servers are configured under mcp_servers. Vibe supports http, streamable-http, and stdio transports. You can set URLs, headers, API key environment variables, commands, arguments, environment variables, startup timeouts, and tool execution timeouts.

MCP tool names use the pattern {server_name}_{tool_name}, so a fetch server tool might appear as fetch_server_get. You can assign tool permissions to MCP tools the same way you assign permissions to built-in tools.

Session Management

Use vibe --continue or vibe -c to continue the most recent saved session. Use vibe --resume SESSION_ID to resume a specific session. Session logging must be enabled for these features.

Use --workdir to choose a working directory and --add-dir to make additional directories available for a session. Added directories are implicitly trusted and can contribute their own instructions, configuration, skills, prompts, and agents.

Updates, Notifications, and Telemetry

Auto-update is enabled by default. Set enable_auto_update = false in config.toml to disable it. Notifications can alert you when the agent needs approval, asks a question, or completes a task. Set enable_notifications = false to disable them.

Use of Vibe can include collection and processing of usage data. You can disable telemetry by setting enable_telemetry = false in config.toml. If you work with private code, client projects, or regulated data, check this setting before you start a session.

Mistral Vibe vs Claude Code

Mistral Vibe and Claude Code solve the same basic problem: you describe a software task, the agent reads project context, edits files, runs tools, and returns changes for review. The difference is in the model family, product surface, pricing, openness, and how much you care about remote coding sessions.

Price is only part of the decision. Vibe is more appealing if you want an inspectable CLI project, custom skills, explicit tool filtering, and Mistral’s Devstral-oriented coding stack. Claude Code has the stronger mindshare and a larger Anthropic ecosystem around Claude plans, cloud coding, remote control, and organization use cases. For paid daily coding, test both on the same repository task and compare diff quality, command safety, context handling, and how often you need to step in.

Pros

• Free entry point: You can try Vibe before paying, although free coding access is limited.
• Lower individual paid price than Claude Pro: Mistral Pro is $14.99/month, while Claude Pro is $20/month when billed monthly.
• Open-source CLI: The Mistral Vibe CLI is an Apache 2.0 project, so developers can inspect the code and follow releases.
• Detailed local controls: The CLI has custom agents, skills, prompts, MCP servers, tool permissions, session controls, and trust folders.
• Good fit for repeatable engineering tasks: Skills and slash commands work well for repo-specific checklists, reviews, testing, and documentation.

Cons

• Free plan limits: The Free plan only gives limited coding sessions, so heavy Vibe Code use requires a paid plan or pay-as-you-go extension.
• Python 3.12+ requirement: The CLI requires a modern Python environment. Older systems may need runtime updates before installation.
• UNIX-first support target: Windows works, but the project targets UNIX environments first.
• Permission risk: Coding agents can modify files and run shell commands. Review trusted folders, approvals, tool permissions, and generated diffs carefully.
• Configuration depth: New users may need time to understand agents, skills, MCP servers, prompts, telemetry, and session settings.

Alternatives & Related Resources

• Mistral Vibe GitHub Repo: Access the open-source CLI code, documentation, releases, and issues.
• Mistral Pricing: Check the current Free, Pro, Team, Education, Enterprise, and API pricing details.
• Mistral Vibe for VS Code: Install the VS Code extension for editor-based coding sessions.
• Mistral Platform Console: Manage Mistral API keys and account settings.
• Best CLI AI Coding Agents: Compare Mistral Vibe with other popular terminal-based AI coding agents.

FAQs

Q: Is Mistral Vibe free?
A: Mistral Vibe has a Free plan with limited Vibe access and limited coding sessions. It is suitable for trying the agent, but daily coding work belongs on the Pro plan or higher.

Q: How much does Mistral Vibe Pro cost?
A: Mistral Pro costs $14.99 per month, excluding taxes. It includes full access to Vibe for long-running tasks plus all-day coding in the CLI, IDE, and web, subject to fair usage limits.

Q: Is Mistral Vibe only a CLI coding agent?
A: No. The CLI is one part of Vibe Code. Mistral Vibe also includes web-based Vibe, Work Mode, mobile access, supported IDE contexts, and remote coding sessions.

Q: Does Mistral Vibe require an API key?
A: The CLI requires Mistral account credentials or an API key. You can configure the key during first launch, with vibe --setup, through MISTRAL_API_KEY, or through ~/.vibe/.env.

Q: Does Mistral Vibe work on Windows?
A: Mistral Vibe works on Windows, but the project targets UNIX environments. Windows users should expect more setup friction.

Q: How does Vibe compare to Claude Code?
A: Vibe is the better fit if you want Mistral’s model ecosystem, a lower individual Pro price, an open-source CLI, and detailed local configuration. Claude Code is the better fit if you already use Claude heavily or prefer Anthropic’s connected coding ecosystem.

Q: Can I disable Mistral Vibe telemetry?
A: Yes. Set enable_telemetry = false in config.toml. You should check this setting before using Vibe with private code, client work, or regulated data.

Q: Can I use Mistral Vibe with MCP servers?
A: Yes. Vibe supports MCP servers over http, streamable-http, and stdio transports. You can configure headers, API keys, commands, environment variables, timeouts, and per-tool permissions.

Changelog

June 2026 update:

• Replaced the old unlimited-free wording with current Free, Pro, Team, Education, Enterprise, and API pricing details.
• Added CLI coverage for built-in agents, subagents, trust folders, programmatic mode, voice mode, skills, MCP servers, session management, updates, notifications, and telemetry.
• Added a dedicated Mistral Vibe vs Claude Code comparison section.
• Expanded the FAQ with pricing, Windows support, API key setup, telemetry, and MCP questions.