Getting started
Install, sign in, and run a first request
Set up a licensed desktop workspace and safely verify a small task.
Vopit documentation
Practical, source-backed guidance for projects, agents, models, infrastructure, operations, and recovery.
Getting started
Set up a licensed desktop workspace and safely verify a small task.
Getting started
Understand desktop access, connected computers and model-provider sign-in.
Getting started
Use the studio interface, give agents useful context, and recover safely.
Getting started
Work with your team from a terminal with the vopit command, or let scripts and AI models drive Vopit.
Getting started
Give a coding agent such as Claude Code or Codex the vopit command, so it can set up and run your team while you keep the decisions.
Getting started
Follow your agents, send requests, answer permissions, and run the Board, Cranks and meetings from vopit.fr/remote.
Getting started
Keep Vopit up to date and connect through a company network that inspects HTTPS traffic.
Connections & models
Connect ChatGPT, APIs, compatible endpoints, local models, or supported CLIs.
Connections & models
Verify the local command-line integration and understand its execution boundary.
Connections & models
Complete browser sign-in, select an account and model, and verify a real request.
Connections & models
Load a locally installed model, set the endpoint, and distinguish discovery from inference.
Connections & models
Configure API access, model inheritance, reasoning effort, response checks, and optional rates.
Connections & models
Configure app actions, custom APIs, triggers and ordered steps for your agents.
Agents
Define a mission, tools, model, behavior, and deliverable contract.
Agents
Understand routing, parallel work, reviews, and after-success ticket creation.
Agents
Understand inactivity deadlines, refusals, structured results, dependencies and saved work.
Agents
Publish your team and studio, inspect community missions, and import an editable copy.
Agents
Create a team with AI or the native team, recover a previous studio, import a scene or return to team selection.
Agents
Talk through an idea with several agents at once, ask one for a quick task, then apply the facts, instruction changes and actions you choose.
Agents
Choose how much thinking the team spends, and let requests of one project run side by side in separate Git worktrees.
Permissions & safety
Make least-privilege decisions for local tools, providers, and exports.
Infrastructure
Configure deployment targets, reusable operations, approved agent proposals and per-agent grants.
Infrastructure
Run an explicit, reviewable release sequence for an already prepared server.
Infrastructure
Choose reviewed operations for containers, application services, clusters, static sites and database migrations.
Projects & context
Interpret what Vopit stores, sends, and reports.
Projects & context
Inspect a session, preserve evidence, recover safely, and remove saved records deliberately.
Projects & context
Prepare a feature branch before work and commit eligible files after the workflow.
Projects & context
Inspect memory, code dependencies, agent handoffs and local history in one place.
Projects & context
Organize a project’s work in columns, start cards as requests, plan with AI and sync with Trello or Jira.
Projects & context
Let one workspace span several folders, and review, commit and synchronize changes from the Changes panel.
Reference
A concise map of active defaults, limits, and where settings apply.
Reference
Use the symptom, scope, correction, and verification sequence.
Reference
Quick answers and common Vopit terminology.
Reference
Arrange the room, choose appearance, use quick actions, and navigate without guessing shortcuts.
Reference
Match every configurable action to its engine, permission and execution boundary.