# mistralai/mistral-vibe

Minimal CLI coding agent by Mistral

Repository: https://github.com/mistralai/mistral-vibe
Canonical: https://ross.abutalabs.com/products/mistral-vibe
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T15:19:50+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 19
- inputs: {"age_days": 268, "days_push": 7, "days_rel": 7, "gap_med": 2, "n_releases_24m": 82}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4876, forks 656 (observed 2026-08-28T04:09:01.725603+00:00)

## What it is
Mistral Vibe is an open-source command-line coding agent powered by Mistral's models, providing a conversational interface to explore and modify codebases with tools, subagents, skills, and MCP server support. It is installed via pip/uv or a one-line script and targets UNIX environments primarily.

## Use cases
- refactor code from the terminal with natural language
- explore an unfamiliar codebase conversationally
- run an AI coding agent in the CLI
- delegate coding tasks to subagents
- extend a coding assistant with custom skills and MCP servers

## When to choose
- you want a lightweight terminal-based AI coding assistant
- you prefer Mistral models over other providers
- you need programmable/interactive agent modes and MCP integration

## When to avoid
- you need first-class Windows support
- you want an IDE-integrated GUI assistant
- you require models from other providers only

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools, mcp
- domain: developer-tools, large-language-models
- platform: cli, windows, python
- tags: coding-assistant, terminal-agent, mistral, agentic-coding, skills, voice-mode, ai-agents, command-line, linux, macos

## Member repositories
- mistralai/mistral-vibe (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.725603+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:18:17.710087+00:00, confidence not recorded.
  - readme: https://github.com/mistralai/mistral-vibe (fetched 2026-08-28T04:09:01.725603+00:00, sha ebc1fd99d663)
  - registry_pypi: https://pypi.org/pypi/mistral-vibe/json (fetched 2026-08-29T09:00:41.679548+00:00, sha df12c8574b76)
- Data as of 2026-08-30T08:39:29.467469+00:00.