Skip to main content
Help Center
General · AI & Models

Choose the brain that helps me think

I can think all by myself, or you can plug in a smarter brain — one running on your own computer, or a big cloud one. Here's what each choice means, in plain words.

4 min read · Updated 7/5/2026

On this page

A little secret: the "brain" that helps me read your links and understand your questions can be swapped out. I come with a simple built-in brain, but you can plug in a smarter one — on your own computer, or a big one in the cloud. Here's what each choice means.

What it is

Behind the scenes, I use an AI model to write titles, pick tags, and understand what you're asking for. You get to choose which model I use. There are three routes, and you can switch anytime.

Why you'll love it

  • Start clever for free — no setup, no keys.
  • Go fully private with a model on your own machine.
  • Or plug in a top cloud model if you already have one.

Your three choices

  1. My built-in brain (offline). Works out of the box, needs nothing, and never sends your saves anywhere. It's simple but honest, and always available.
  2. A model on your own computer. Run Ollama or LM Studio and point me at it. Private, free, and quite clever — see Use Ollama or LM Studio.
  3. A big cloud model. Bring your own key from OpenAI, Anthropic (Claude), Gemini, Grok, or Perplexity — see Use OpenAI, Claude, Gemini, Grok, or Perplexity. Or let us run one for you on Pro — see Let us run the smart brain for you.

How to use it

  1. Open Settings and find the AI section.
  2. Pick which brain I should use.
  3. Save. That's it — I'll start using it right away.
Which should you pick? If you just want it to work, start with the built-in brain or our managed one. If you care most about privacy, use a local model. If you already pay for OpenAI or Gemini, plug that in.

Good to know

  • Choosing a model is Free; some cloud options cost money on the provider's side, or need Pro for our managed brain.
  • Whatever you choose, your saves stay yours — a local model keeps everything on your machine.

Where to next