# Mistral Vibe Mistral’s assistant and agent for work and code (formerly Le Chat) on the web, in the app, in the terminal and in the editor. Canonical profile: https://ki-agentenkompass.de/en/agents/mistral-vibe/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Vibe is the new name of Le Chat; conversations, settings and plans carried over. According to the documentation, the open-source mistral-vibe CLI is the tool of Vibe Code and therefore belongs in this profile. - Provider: Mistral AI - Product family: Mistral Vibe - Profile type: Assistant and agent for work and code - Environment: Web and mobile app (Work), terminal CLI for macOS, Linux and Windows, VS Code extension, Vibe Code Web - Connections: Connectors (over 100 tools according to the product page), MCP, skills, GitHub, VS Code, JetBrains and Zed - Setup: Sign in on the web with a Mistral account. For code you install the CLI and sign in through the browser or with an API key. - Pricing model: There is a free plan; Pro costs 14.99 US dollars a month, Team 24.99 per user, Enterprise on request. The CLI is under Apache-2.0. ## Key features ### Vibe Work for research and documents According to the product page, Vibe researches the web and internal documents, analyses data, drafts documents and decks and uses over 100 connectors. Source: https://mistral.ai/products/vibe ### Vibe Code: CLI, editor, web The CLI and VS Code extension work on a local checkout, Vibe Code Web on a GitHub repository in a remote sandbox. Source: https://docs.mistral.ai/vibe/code/overview ### Scheduled tasks A saved prompt runs once or daily, weekly, monthly or yearly. The feature is in public preview and runs in Work mode only. Source: https://docs.mistral.ai/vibe/work/scheduled-tasks ### Knowledge Base The Knowledge Base (successor to Chat Memories, Work mode only) keeps details from conversations and can be viewed, changed through chat, deleted and exported. Source: https://docs.mistral.ai/vibe/work/knowledge ### Approval modes in the CLI The profiles ask, accept-edits (default), smart-approve and auto-approve control what Vibe does without asking. Project configuration loads only from trusted folders. Source: https://docs.mistral.ai/vibe/code/safety-approvals-permissions ### Skills, MCP and subagents You extend the CLI with skills, MCP servers, AGENTS.md and custom subagents; a read-only explore subagent is built in. Source: https://github.com/mistralai/mistral-vibe ### Remote coding sessions Vibe Code Web runs tasks in a managed cloud sandbox and ends each session with a branch or pull request for review. Source: https://docs.mistral.ai/vibe/code/vibe-code-web/get-started ## Example workflows ### Weekly research with report - Your input: A prompt with source guidance, set up as a scheduled task in Work mode. - Possible result: The prompt runs at the chosen time and the result appears as a notification in the sidebar. - What to check: Read the result and sources; pre-authorise only read actions for unattended runs. ### Code change in the CLI - Your input: A trusted project folder with AGENTS.md and a limited task. - Possible result: Vibe changes files and asks about shell commands. - What to check: Check the diff and tests; use auto-approve only in isolated environments. ## Requirements and limits ### Account or API key Requirement: For Mistral-hosted models the CLI signs in with a Mistral account through the browser or with an API key, and this also works in Free mode. A Mistral account is optional for local models or other OpenAI-compatible keys. Source: https://docs.mistral.ai/getting-started/quickstarts/vibe-code/install-cli ### Python 3.12 for manual installation Requirement: The CLI needs a GIL-enabled build of Python 3.12 or later; uv can install it. On Windows it works per the README, but UNIX is the officially supported target. Source: https://github.com/mistralai/mistral-vibe ### Scheduled tasks: preview and pre-authorisation Limitation: Sensitive connector actions such as sending email need a pre-granted Always allow for unattended runs. The page recommends read-only prompts. Source: https://docs.mistral.ai/vibe/work/scheduled-tasks ### Smart approve is not a sandbox Limitation: According to the safety page, smart approve is a classifier, not a sandbox. For untrusted code it recommends the ask profile or an isolated environment. Source: https://docs.mistral.ai/vibe/code/safety-approvals-permissions ### Zero data retention does not cover Vibe conversations Limitation: The page excludes Vibe Work and Chat because they store conversation data. Organisations on paid plans can request ZDR from support. Source: https://docs.mistral.ai/admin/monitor-comply/zero-data-retention ### Model training on your data Not yet confirmed: The pricing page lists Opt-out three times in its model training row without it being clear which plan each entry belongs to. Source: https://mistral.ai/pricing ### Remote agents, hooks and teleport by plan Not yet confirmed: The pricing page does not say which plan includes these features. Source: https://mistral.ai/pricing ## A good fit if … - you want an assistant for research and documents and a coding agent under one account - you want to use an open-source terminal CLI with a Mistral account or your own API key - you prefer a European provider with data hosted in the EU by default ## Less suitable if … - you need zero data retention for Vibe conversations - you expect unattended tasks without pre-authorised connector actions - you expect memory in the CLI as well Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice In the terminal you use Mistral models by default and pick them by alias. According to the docs, the Vibe Code CLI also works with any model behind an OpenAI-compatible endpoint, including on your own machine. For web and app, the pages checked name only Mistral models and no model choice of your own. - Model families named: Mistral · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes Partly documented · Sources accessed on: 2026-11-05 - [Mistral: Using offline models](https://docs.mistral.ai/mistral-vibe/local) - [GitHub: mistral-vibe](https://github.com/mistralai/mistral-vibe) - [Mistral: Pricing](https://mistral.ai/pricing) - [Mistral: Vibe Work, get started](https://docs.mistral.ai/vibe/work/get-started) ## Europe & regional availability Help articles on storage location and retention, the product page and documentation reviewed. The storage location article does not name Vibe explicitly. The trust centre and privacy policy could not be evaluated. Reviewed scope: Cloud assistant with a local CLI; Mistral AI is a European provider Reviewed on: 2026-11-05 ### Data hosted in the EU by default With requirements The help article on storage location says data is hosted in the EU by default; if you choose the US API endpoint, it is hosted in the United States. Depending on the feature, data may temporarily go to subprocessors outside the EU. Enterprise customers can have some of these features turned off at organisation level. The article does not name Vibe or Le Chat explicitly. Region covered: EU/EEA Documented reason: Statement on storage location with exceptions; the article does not name Vibe. Official source: https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data Official source: https://mistral.ai/products/vibe ### Availability by country: no statement Availability still unclear The reviewed pages give no country list for Vibe. The product page mentions full data residency for enterprise customers deploying on-premises, in a private cloud or on Mistral Cloud, without naming a location. Region covered: EU/EEA, United Kingdom and Switzerland Documented reason: The reviewed sources name no country release for this. Official source: https://mistral.ai/products/vibe Official source: https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Mistral account for web and CLI, alternatively an API key Sources reviewed: 2026-11-05 ### Account used Documented: Vibe opens at chat.mistral.ai with the existing Le Chat login. The CLI signs in through the browser with a Mistral account (recommended) or takes an API key. Enterprise lists SAML SSO. Evidence: https://help.mistral.ai/en/articles/682992-le-chat-is-now-vibe Evidence: https://docs.mistral.ai/getting-started/quickstarts/vibe-code/install-cli Evidence: https://mistral.ai/pricing ### Admin approval Documented with conditions: Administrators can disable auto-approve and turn off the Knowledge Base organisation-wide. For enterprise organisations, admins can set the date of the merge of Chat and Work themselves. Evidence: https://docs.mistral.ai/vibe/code/safety-approvals-permissions Evidence: https://docs.mistral.ai/vibe/work/knowledge Evidence: https://docs.mistral.ai/vibe ### Data access & team sharing Documented: Work asks before sensitive actions such as sending email. Vibe Code asks before shell commands and by default applies file edits without asking. Access outside the working directory and to .env files requires confirmation. Evidence: https://docs.mistral.ai/vibe/work/get-started Evidence: https://docs.mistral.ai/vibe/code/overview Evidence: https://docs.mistral.ai/vibe/code/safety-approvals-permissions ## Prices and included usage Pricing checked: 2026-11-05 Free costs nothing, Pro 14.99 US dollars a month excluding taxes, Team 24.99 per user per month; Enterprise is on request. ### Free 0 US dollars Limited messages, web searches and coding sessions; basic image generation and editing; 100+ connectors; web and mobile. Price source: https://mistral.ai/pricing ### Pro 14.99 US dollars per month (excl. taxes) Higher limits, faster responses, all-day coding in CLI, IDE or web, 15 US dollars of API credits a month. Price source: https://mistral.ai/pricing ### Team 24.99 US dollars per user per month (excl. taxes) Higher limits, up to 30 GB storage per user, domain verification, data export. Price source: https://mistral.ai/pricing ### Enterprise On request Custom models, agents and workflows, audit logs, SAML SSO, white label, custom deployments (self-hosted, private cloud or on-premises). Price source: https://mistral.ai/pricing Besides 24.99 US dollars for Team, the pricing page also lists 50 US dollars a month without making clear what it applies to. Pro for verified students costs 5.99 US dollars per the page. Beyond the limits you can continue with pay-as-you-go credits at API rates. Pricing details: https://mistral.ai/pricing ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Web app, CLI and Vibe Code Web Sources reviewed: 2026-11-05 ### Files and working state Documented: Conversations and the Knowledge Base persist in Vibe Work, and CLI sessions can be resumed if session logging is enabled. On Vibe Code Web, past sessions can be inspected but not resumed once the sandbox is deprovisioned. Evidence: https://docs.mistral.ai/admin/monitor-comply/zero-data-retention Evidence: https://docs.mistral.ai/vibe/work/knowledge Evidence: https://github.com/mistralai/mistral-vibe ### Sign-ins Documented: The CLI signs in through the browser or stores an API key, per the README in ~/.vibe/.env. The reviewed pages do not say how long a sign-in lasts. Evidence: https://docs.mistral.ai/getting-started/quickstarts/vibe-code/install-cli Evidence: https://github.com/mistralai/mistral-vibe ### Starting further runs Documented: Scheduled tasks run once or daily to yearly without you, in Work mode and as a public preview. The CLI runs programmatically with vibe --prompt, Vibe Code Web asynchronously in a cloud sandbox. Evidence: https://docs.mistral.ai/vibe/work/scheduled-tasks Evidence: https://github.com/mistralai/mistral-vibe Evidence: https://docs.mistral.ai/vibe/code/vibe-code-web/get-started ### Human intervention Documented: Sensitive actions need confirmation; for unattended scheduled tasks you must pre-authorise connector actions with Always allow. In programmatic mode Vibe denies calls that would need approval unless you pass --auto-approve. Evidence: https://docs.mistral.ai/vibe/work/scheduled-tasks Evidence: https://docs.mistral.ai/vibe/code/safety-approvals-permissions ### Detecting errors Open in reviewed sources: The scheduled tasks page describes notifications when a result is ready; the retrieved version contains no details on behaviour on failure. Evidence: https://docs.mistral.ai/vibe/work/scheduled-tasks ### Resuming after failures Documented: Scheduled tasks can be edited, paused, resumed and deleted; results stay in the history after deletion. In the CLI, --resume and --continue resume sessions. Evidence: https://docs.mistral.ai/vibe/work/scheduled-tasks Evidence: https://github.com/mistralai/mistral-vibe ### Editorial assessment Approvals are finely adjustable, but autonomy depends on your profiles and pre-authorisations. For scheduled tasks, prefer read-only prompts and check the results. ## Memory and conversation continuity Scope: Knowledge Base and conversations in Vibe Work; session logs of the CLI Sources accessed: 2026-11-05 Vibe Work keeps details in a visible Knowledge Base that you can view, delete and export; the CLI resumes sessions but describes no memory. ### Storage and scope Documented: Vibe stores conversation data so you can use your history; the Knowledge Base holds entries with a title and description. The CLI writes session logs under ~/.vibe/logs/ when session logging is enabled. - [Mistral: Zero data retention](https://docs.mistral.ai/admin/monitor-comply/zero-data-retention) - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) - [mistral-vibe README](https://github.com/mistralai/mistral-vibe) ### Selection and timing Documented: Entries are created explicitly (“remember”, “save”) or implicitly when Vibe detects recurring useful details. For the CLI, the README describes no memory feature. - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) - [mistral-vibe README](https://github.com/mistralai/mistral-vibe) ### Inspect, edit and delete Documented: You see each entry, cannot edit the text directly but ask Vibe in chat to change it, and delete a topic through the menu. Deleting everything is irreversible; settings allow an export. - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) ### Agent and channel boundaries Partly documented: The Knowledge Base exists in Work mode only; admins can disable it organisation-wide. The page describes no split by person, workspace or project. The CLI’s project configuration loads only from explicitly trusted folders. - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) - [Mistral: Safety, approvals and permissions](https://docs.mistral.ai/vibe/code/safety-approvals-permissions) ### Retrieval Documented: Vibe reviews the entries at each turn to decide which are relevant; retrieval is not deterministic. A read or write pill shows accesses. In the CLI, --resume (picker) and --continue reopen earlier sessions. - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) - [mistral-vibe README](https://github.com/mistralai/mistral-vibe) ### Session reset and compaction Partly documented: In the CLI, /clear starts a new conversation; /compact compacts it while, per the README, the same session stays. For Vibe Work, the reviewed page describes no such command. - [mistral-vibe README](https://github.com/mistralai/mistral-vibe) - [Mistral: Knowledge Base](https://docs.mistral.ai/vibe/work/knowledge) ## Context An account, limited usage on the free plan and a manageable task. Scheduled tasks run in Work mode only and are in public preview. Product page, documentation, pricing page, help articles and repository reviewed. Feature descriptions come from the provider; example tasks are editorial. The trust centre and privacy policy could not be evaluated. Hands-on tests are still pending. ## Open points Europe, availability still unclear: - Availability by country: no statement Requirements and limits, not yet confirmed: - Model training on your data - Remote agents, hooks and teleport by plan ## Sources - https://mistral.ai/products/vibe - https://docs.mistral.ai - https://docs.mistral.ai/vibe - https://mistral.ai/pricing - https://github.com/mistralai/mistral-vibe - https://docs.mistral.ai/getting-started/quickstarts/vibe-code/install-cli - https://docs.mistral.ai/vibe/code/overview - https://docs.mistral.ai/vibe/code/safety-approvals-permissions - https://docs.mistral.ai/vibe/work/get-started - https://docs.mistral.ai/vibe/work/knowledge - https://docs.mistral.ai/vibe/work/scheduled-tasks - https://docs.mistral.ai/vibe/code/vibe-code-web/get-started - https://docs.mistral.ai/admin/monitor-comply/zero-data-retention - https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data - https://help.mistral.ai/en/articles/347628-how-long-do-you-store-my-data - https://help.mistral.ai/en/articles/682992-le-chat-is-now-vibe ## Provider Mistral AI develops the models and offers Vibe as a product for work and code. The mistral-vibe repository contains the CLI under Apache-2.0. - Operator: Mistral AI - Organization: Provider - Website: https://mistral.ai - Reviewed: 2026-11-05 - Repository: https://github.com/mistralai/mistral-vibe - GitHub-Stars: 5303 (2026-11-05) - License: Apache-2.0 - Provider source: https://mistral.ai/products/vibe - Provider source: https://github.com/mistralai/mistral-vibe [Sources and method](https://ki-agentenkompass.de/en/sources/)