Alone, with Pirol Online, or on your own server

kyte always reads and writes a database on the machine in front of you. That is not a cache; it is the real thing. What differs between the three arrangements is only what that database synchronises with.

On your own

Nothing to set up and nothing leaves the building except what you send to the model. One person, one machine, everything local.

This is where most installations start, and for a one-person company it can be where they stay.

With Pirol Online

Your workspace also lives on a server run by Pirol. Several people and several devices see the same data, each device holding the part its user is allowed to see.

Pick this when colleagues need the same workspace and you do not want to run a server.

On your own server

The same, but the server is yours — a machine in your office running the Pirol stack. The data never leaves your network, and the AI models can run there too, in which case a conversation does not leave the building at all — see which model answers.

Pick this when where the data physically sits is a question you have to answer to someone.

Changing your mind

The choice is not a one-way door. A workspace that starts alone can get a server later, and the app behaves the same in all three: local first, synchronised afterwards.

What you see in Settings → Storage tells you which one you are in today.