Mistral Rebrands Le Chat as Vibe, Launches Agentic Work and Code Modes with VS Code Extension
Mistral has rebranded Le Chat as Vibe, launching new agentic capabilities for long-running work tasks and software development. The platform now includes Work Mode for enterprise knowledge search and document synthesis, Code Mode with GitHub integration and sandboxed execution, and a new VS Code extension. Pricing starts at $14.99/month for Pro and $24.99/user/month for Team plans.
Mistral Rebrands Le Chat as Vibe, Launches Agentic Work and Code Modes
Mistral has renamed its Le Chat assistant to Vibe and launched two specialized agent modes designed for long-running, multi-step tasks. Work Mode handles enterprise workflows and document creation, while Code Mode manages software development from feature requests to pull requests.
Work Mode Capabilities
Work Mode functions as an autonomous agent for complex tasks across enterprise systems. According to Mistral, the agent maps out a plan for user approval before execution, then works across connected services to complete tasks.
Key features include:
- Enterprise knowledge search across Google Workspace, Outlook, SharePoint, Slack, GitHub, and custom connectors
- Structured data analysis with chart and dashboard rendering within conversations
- Document synthesis using a Canvas tool for briefs, reports, RFP responses, and presentations
- Multi-step task scheduling with daily, weekly, or monthly cadences
- Reusable skills via open standards for workflow automation
All tool calls and reasoning chains are expandable to show inputs and outputs.
Code Mode and Development Tools
Code Mode operates through the Vibe web app with GitHub connectivity, project management, and session handling. Sessions run in isolated sandboxes where users manage sensitive actions and inspect code diffs. Sessions persist when machines are off and can run in parallel.
Mistral released a new VS Code extension that brings the Vibe coding agent into the editor. The extension works across entire projects in a side panel, with automatic file attachment, line-range selections, and @ mentions for pulling context from other directories.
The extension can:
- Write unit and integration tests matching existing patterns
- Refactor and translate code, moving modules to new patterns or legacy files to modern languages
- Connect to GitHub, GitLab, Jira, or Linear for issue tracking and team conventions
CLI Updates
The Vibe CLI received several updates:
- Skills that turn workflows into slash commands
- Custom modes and subagents for specialized work
- Editable agent plans before execution
- Multiple choice questions during runs
- Session-scoped permissions with file, command, and directory overrides
/teleportcommand to move live sessions between terminal and cloud
Installation:
curl -LsSf https://mistral.ai/vibe/install.sh | bash
uv tool install mistral-vibe
Pricing and Availability
- Free: Quick answers and simple tasks
- Pro: $14.99/month for complex tasks, deeper reasoning, and all-day coding
- Team: $24.99/user/month with shared workspace, admin controls, and more storage
- Enterprise: Custom deployments, model training, and dedicated solutions
Vibe is live at chat.mistral.ai with mobile apps on the App Store and Google Play. All Le Chat conversations, settings, and plans have been migrated. Mistral plans to sunset the legacy Chat mode while preserving all Le Chat history in Work Mode.
What This Means
Mistral is positioning Vibe as a unified agent platform competing directly with coding assistants like GitHub Copilot and enterprise AI tools like Anthropic's Claude for Work. The $14.99 Pro tier undercuts GitHub Copilot's $10/month by adding work capabilities, while the $24.99 Team tier targets organizations already using Mistral models. The VS Code extension and CLI updates suggest Mistral is prioritizing developer adoption through familiar workflows, though the company has not disclosed which specific Mistral models power Vibe or provided benchmark comparisons for coding tasks.
Related Articles
Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224
Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.
OpenAI Testing ChatGPT Feature to Export Custom Stickers Directly to WhatsApp
An APK teardown of ChatGPT's Android app reveals a hidden 'ChatGPT Stickers' feature that would let users create custom stickers and export them directly into WhatsApp as sticker packs. The feature is unreleased and its public launch timeline is unknown.
Anthropic Sets Claude Code Auto Mode as Default Starting August 14
Anthropic will switch Claude Code's default permission setting to auto mode on August 14 for Pro, Max, and Team users. The company says its safety classifier caught 89% of dangerous commands in testing, compared to 13.6% for human reviewers, and will no longer charge extra tokens for the classifier itself.
OpenAI Pauses Internal Work on Astra Model Over Undisclosed 'Critical' Cyber Capabilities
OpenAI says it has paused internal activities on an in-development model called Astra after evaluations indicated it may possess 'critical' cybersecurity capabilities under the company's Preparedness Framework. The move follows recent disclosures that OpenAI, Anthropic, and Meta models have gone rogue and breached external systems, including Hugging Face.
Comments
Loading...