mistralai/mistral-vibe

mistralai/mistral-vibe

Description: Minimal CLI coding agent by Mistral

Language: Python

License: Apache-2.0

Stars: 4435

Forks: 525

Open issues: 263

Created: 2025-12-08T18:56:59Z

Pushed: 2026-06-08T13:00:20Z

Default branch: main

Fork: no

Archived: no

README:

Mistral Vibe


██████████████████░░
██████████████████░░
████ ██████ ████░░
████ ██ ████░░
████ ████░░
████ ██ ██ ████░░
██ ██ ██░░
██████████████████░░
██████████████████░░

Mistral's open-source CLI coding assistant.

Mistral Vibe is a command-line coding assistant powered by Mistral's models. It provides a conversational interface to your codebase, allowing you to use natural language to explore, modify, and interact with your projects through a powerful set of tools.

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

One-line install (recommended)

Linux and macOS

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

Windows

First, install uv

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then, use uv command below.

Using uv

uv tool install mistral-vibe

Using pip

pip install mistral-vibe

Table of Contents

• [Features](#features)
• [Built-in Agents](#built-in-agents)
• [Subagents and Task Delegation](#subagents-and-task-delegation)
• [Interactive User Questions](#interactive-user-questions)
• [Terminal Requirements](#terminal-requirements)
• [Quick Start](#quick-start)
• [Usage](#usage)
• [Interactive Mode](#interactive-mode)
• [Trust Folder System](#trust-folder-system)
• [Programmatic Mode](#programmatic-mode)
• [Voice Mode](#voice-mode)
• [Slash Commands](#slash-commands)
• [Built-in Slash Commands](#built-in-slash-commands)
• [Custom Slash Commands via Skills](#custom-slash-commands-via-skills)
• [Skills System](#skills-system)
• [Creating Skills](#creating-skills)
• [Skill Discovery](#skill-discovery)
• [Managing Skills](#managing-skills)
• [Configuration](#configuration)
• [Configuration File Location](#configuration-file-location)
• [API Key Configuration](#api-key-configuration)
• [Custom System Prompts](#custom-system-prompts)
• [Custom Agent Configurations](#custom-agent-configurations)
• [Tool Management](#tool-management)
• [MCP Server Configuration](#mcp-server-configuration)
• [Session Management](#session-management)
• [Update Settings](#update-settings)
• [Custom Vibe Home Directory](#custom-vibe-home-directory)
• [Editors/IDEs](#editorsides)
• [Resources](#resources)
• [Data collection & usage](#data-collection--usage)
• [License](#license)

Features

• Interactive Chat: A conversational AI agent that understands your requests and breaks down complex tasks.
• Powerful Toolset: A suite of tools for file manipulation, code searching, version control, and command execution, right from the chat prompt.
• Read, write, and patch files (read, write_file, edit).
• Execute shell commands in a stateful terminal (bash).
• Recursively search code with grep (with ripgrep support).
• Manage a todo list to track the agent's work.
• Ask interactive questions to gather user input (ask_user_question).
• Delegate tasks to subagents for parallel work (task).
• Project-Aware Context: Vibe automatically scans your project's file structure and Git status to provide relevant context to the agent, improving its understanding of your codebase.
• Advanced CLI Experience: Built with modern libraries for a smooth and efficient workflow.
• Autocompletion for slash commands (/) and file paths (@).
• 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.
• Persistent command history.
• Beautiful Themes.
• Highly Configurable: Customize models, providers, tool permissions, and UI preferences through a simple config.toml file.
• Safety First: Features tool execution approval.
• Multiple Built-in Agents: Choose from different agent profiles tailored for specific workflows.

Built-in Agents

Vibe comes with several built-in agent profiles, each designed for different use cases:

• `default`: Standard agent that requires approval for tool executions. Best for general use.
• `plan`: Read-only agent for exploration and planning. Auto-approves safe tools like grep and read.
• `accept-edits`: Auto-approves file edits only (write_file, edit). Useful for code refactoring.
• `auto-approve`: Auto-approves all tool executions. Use with caution.

Use the --agent flag to select a different agent:

vibe --agent plan

To change the default agent used when --agent is not passed, set default_agent in your config.toml:

default_agent = "plan"

Valid values are default, plan, accept-edits, auto-approve, lean (only when listed in installed_agents), or the name of any custom agent file in ~/.vibe/agents/ or the project's .vibe/agents/ directory. Subagents such as explore are not accepted.

> Note: default_agent only applies to interactive sessions. In > programmatic mode (-p / --prompt), Vibe falls back to auto-approve > when --agent is not provided, so default_agent is ignored.

Subagents and Task Delegation

Vibe supports subagents for delegating tasks. Subagents run independently and can perform specialized work without user interaction, preventing the context from being overloaded.

The task tool allows the agent to delegate work to subagents:

> Can you explore the codebase structure while I work on something else?

🤖 I'll use the task tool to delegate this to the explore subagent.

> task(task="Analyze the project structure and architecture", agent="explore")

Create custom subagents by adding agent_type = "subagent" to your agent configuration. Vibe comes with a built-in subagent called explore, a read-only subagent for codebase exploration used internally for delegation.

Interactive User Questions

The ask_user_question tool allows the agent to ask you clarifying questions during its work. This enables more interactive and collaborative workflows.

> Can you help me refactor this function?

🤖 I need to…