Privacy while you work
What leaves your machine, what never does, and what happens to a request when a cloud model is faster.
What actually leaves your machine
0:48
The local filter, and the difference between on-device and hosted models.
Files, sources and trust
1:04
Citation ranking and generated files, shown live.
Local models
Nothing leaves the machine. The model runs on your own hardware, the prompt never crosses the network, and there is no request for anyone to log. This is the default.
Cloud models
When you choose a hosted model, the request is anonymised before it leaves your machine, so the provider sees the work but not who is asking. What they receive is the prompt you sent — so the usual rule still applies: do not paste a secret into a request you are sending to a third party.
What is stored
•
Conversations are kept locally, and synced to your account when you are signed in so other devices can see them.
•
Usage and billing are recorded per request, which is what /status and the usage page read.
•
You can delete an individual conversation, or your whole account and everything attached to it, from the account page.
Working offline
With a model pulled, the network is optional. Work done offline merges cleanly with your history the next time you reconnect, and unused offline token allowance goes back to your balance.
All documentation
Installation
Install the CLI on macOS, Linux or Windows, and sign in.
Setup, start to finish
The whole path on one page: install, sign in, pick local or hosted, get an answer.
Connecting accounts
One account everywhere, registering devices for the SMS bridge, and OAuth integrations.
Models
Pull open-weight models, switch between them, and run fully local.
Using models on every client
What runs locally in a terminal, a browser tab, a phone and the desktop app.
Commands
Every terminal command and every slash command, each with its own page.
Editor integrations
VS Code, Cursor, JetBrains, Neovim, Sublime, Zed, Godot, Unity, gh and git hooks.
The SMS bridge
Send a task to your own machine from your phone, and get the answer back.
The apps
One React Native codebase behind iPhone, Android, web and desktop — and how to run it.
Automation Studio
Idea to production: flows, per-step models, your machines or ours, live editing.
Enterprise seats
Licensed team seats under one owner account — invites, billing, and how seats resolve.
API reference
API keys, authentication, chat completions, pricing and errors — for your own software.
Notifications
Four channels, all opt-in, how to change them, and the limits on re-engagement.
Troubleshooting
When a model will not load, a command hangs, or the CLI cannot be found.