You want to ask your own notes a question. Or summarise a page you have just finished, or have a passage explained, or draft something out of what you already wrote. MojoPad does all of that, and does it on your own Mac — nothing you write is sent anywhere, there is no account, and there is no subscription.
Getting there takes one free app and about two minutes, and you will not need to type a command anywhere. If you have ever been told to open Terminal and would rather not, this chapter is for you: MojoPad does that part now.
A model that writes is a large piece of software in its own right — several gigabytes of it. Putting one inside MojoPad would make every download that much heavier for everybody, including the many people who never touch these features, and it would be a worse model than the one you can choose for yourself. So MojoPad borrows one from Ollama, a free app whose whole job is to keep models on your Mac and let other apps use them.
Ollama is the only thing you install. MojoPad will not download or run an installer for you, and that is deliberate rather than laziness: the promise this app makes is that nothing happens to your Mac that you did not ask for, and an app that quietly fetches and runs programs has given that promise away. So that one step is yours. Everything either side of it is handled here.
⇧⌘A for Ask Your Wiki, or select
a few words and choose ✦Explain. If there is nothing on this Mac to answer with, MojoPad says
so and offers to set it up. You can also go looking for it deliberately: Set Up Local AI… in
the command palette (⇧⌘P).Models are large: somewhere between two and twenty gigabytes depending on your Mac, which on a normal connection is minutes rather than seconds. It happens once. You can close the window and carry on writing — stopping the download does not break anything, and starting again picks up rather than beginning from nothing.
You do not need a second model for searching. If you have read elsewhere that this needs an "embedding" model, that is a real distinction but not your problem: MojoPad carries its own small one for finding pages by meaning, and offers it separately when it is first needed. The download above is the writing half, and it is the only one you have to think about.
"MojoPad's AI runs on your own Mac, and this one has no model yet." Exactly what it says, and the button beside it opens the setup. This is the normal message before you have done any of the above.
It says Ollama is not running. Ollama is installed but asleep — this happens after a restart if you have not set it to open at login. MojoPad offers to start it for you, and knows the difference between "not installed" and "not running", so trust which one it tells you.
The download stopped. Click Try again. Ollama resumes from where it got to rather than starting over, so a lost connection costs you only the part that had not arrived.
Answers are very slow. The model is probably too large for this Mac to hold comfortably. Run Set Up Local AI… from the command palette again to fetch a smaller one, or see Bring your own model in Local AI, which lets a model somewhere else answer instead.
You would rather it never asked. Settings ▸ AI ▸ Use no AI at all switches off every one of these features and stops MojoPad offering. There is a per-wiki version of the same switch in the Info palette, for a document you would rather no model ever touched.
Local AI is the full chapter: what the two kinds of model actually do, how to choose between models once you have more than one, what runs on your Mac versus what can be sent elsewhere if you allow it, and how to switch any of it off. This chapter only gets you a working one; that one explains what you now have.