mistralai/mistral-vibe

Minimal CLI coding agent by Mistral

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 38 minutes ago
Added to GitGenius on September 14th, 2026
Created on December 8th, 2025
Open Issues & Pull Requests: 300 (+0)
GitHub issues: Enabled
Number of forks: 697
Total Stargazers: 4,951 (+2)
Total Subscribers: 31 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 47.2 hours
Mean response time: 25.7 days
90th percentile: 89.3 days
Tracked items: 368

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "ACP" is answered fastest, typically in about 28 hours, while "linear-sync" waits about 10 days. Almost all tracked open issues have seen activity in the last three months. Only 8% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 126
New in 7 days: 10
Closed in 7 days: 0
Avg open age: 101 days
Stale 30+ days: 81
Stale 90+ days: 0

Recent activity

Opened in 7 days: 8
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • bug (266)
  • CLI (241)
  • linear-sync (181)
  • enhancement (27)
  • VS Code Extension (21)
  • ACP (15)
  • Engineering and Automation (13)
  • Harness: Tools (11)

Detailed Description

Mistral Vibe is a CLI coding agent powered by Mistral's language models that provides a conversational interface to your codebase.

The tool solves the problem of interacting with code through natural language by offering a command-line assistant that can explore, modify, and work with projects. It works through a conversational interface backed by Mistral's models, with access to a set of built-in tools. The agent supports multiple interaction modes including interactive conversation, voice input, and programmatic access. It includes a skills system that allows custom slash commands to be defined and discovered, and integrates with MCP servers for extended tool management. A trust folder system governs which directories the agent can access, and the tool supports custom system prompts and agent configurations.

Developers targeting UNIX environments should note that while the tool runs on Windows, official support focuses on Linux and macOS. The project can be installed via uv or pip. It suits developers who want to interact with their codebase conversationally and who are comfortable with command-line workflows. The tool's extensibility through skills and MCP server integration makes it suitable for teams wanting to customize agent behavior beyond the built-in capabilities. Session management and OpenTelemetry tracing support are available for those needing to track or persist interactions.

The project shows active development with regular updates to its feature set. The codebase demonstrates ongoing refinement of the agent architecture and tool integration systems. Documentation is comprehensive, covering configuration options, skill creation, and multiple usage patterns. The maintainers have invested in making the tool accessible through multiple installation methods and interaction modes, suggesting attention to developer experience across different workflows.