Skip to content

AI & intelligence

Where each AI action lives, Review Links, New Note from a Prompt, typing suggestions, Ask Your Library, the Assistant, and choosing the System model or an MLX model.

On your device

Every AI feature runs on Apple’s Foundation Models, on your own Mac, iPhone or iPad: Apple Intelligence by default — the model the app calls System — or an open model you download and run on your device with MLX. Your notes are processed on the device and are not sent to us or to any AI service. There are no third-party AI services and no API keys. What does leave the device is a web search, when the Assistant or Research looks something up: the search terms go to DuckDuckGo — and the model writes them after reading your question and, often, your notes — and a page it then reads is fetched from that page’s site. Downloading an MLX model fetches its files from Hugging Face.

The AI features are available when the model you have chosen can run. Apple Intelligence needs a device that supports it, with Apple Intelligence turned on — in System Settings on the Mac, Settings on iPhone and iPad. An MLX model needs to be downloaded, or its folder chosen. Otherwise the AI commands are unavailable, and the AI settings say why.

Everything else in HelloNotes works without them — the AI is an addition, never a requirement.

Note actions

These live in the Note menu, beside Rename and Duplicate — not in a panel of their own — and in Note Actions, the menu at the right of the bar over the open note, under the name of the model that will do the work. On iPhone they are also gathered in the AI tab. A suggestion appears in the right panel’s view that already holds that kind of information, so you find it where you would have gone looking anyway.

  • Summarise Note — a short summary of the current note, shown at the top of the Summary & Outline view. A summary is an outline at a different resolution. Save to Properties keeps it in the note’s summary: property.
  • Suggest Tags — proposes tags based on the content, in the Tags view; you choose which to keep.
  • Suggest Links — finds notes that are plausibly related, in the Links view beside the links the note already has.
  • Rewrite or Expand Note… — improve the writing, fix the grammar, make it concise, elaborate, simplify, turn it into bullet points or expand it — or describe the rewrite yourself. You see the result and choose Replace Note or Insert Below; nothing changes until you do.

Selecting text adds the actions that need your notes to make sense to the editor’s own selection menu — a right-click on the Mac, the standard selection menu on iPhone and iPad: Rewrite with AI…, Link to “note” when the phrase names a note you have, Find Related and Ask Your Library. They sit beside Writing Tools, which the system already puts in every text view.

Can’t remember where a command lives? ⇧⌘P — File ▸ Command Palette… — opens a command palette: type a command’s name to run it.

Note ▸ Review Links… (⇧⌘L) walks the note phrase by phrase the way a spell check does — Link, Skip or Never. You see the phrase in its own sentence and the opening lines of the note it would point at, because the same phrase can deserve a link in one paragraph and not the next.

  • Every phrase that names another note is a candidate. When a note turns up more than ten, the ten whose targets are most related to what you are writing are the ones shown — a long note can otherwise produce dozens, and a list nobody finishes reading is a list that gets skipped.
  • Never is remembered for that collection, so a phrase you have rejected stops coming back. It is kept on your device rather than in your notes — a decision you made is not something to commit to a shared repository.
  • Nothing is written until you finish.

This one needs no model at all: it is an exact scan of your own text.

New note from a prompt

File ▸ New Note from a Prompt… (⌃⌘N) — also under the + in the bar over the note — writes a new note, in two modes. Write composes one from a description. Research investigates a question on the web across several angles and lands the answer as a note, with its sources gathered at the end and a record of the question it came from.

Research needs a model with room to read web pages — at least 8,000 tokens. MLX models have that, and so does the System model where Apple Intelligence gives it 8,192 tokens. Research uses the model chosen in Settings ▸ AI, and if that one can’t hold enough, the sheet says so rather than starting a run that cannot finish.

Either way the draft is connected to what you already have: notes you own on the topic are offered as link targets — Research can search and read them as well — and every link that comes back is checked against your collection. Anything naming a note that does not exist is turned back into ordinary text, and the draft says so. A link that looks real but points nowhere is worse than no link.

You read the whole draft — title and body, both editable — before anything is created. Cancel leaves nothing behind. The button is Create Note.

Suggest as I type

Grey text appears after the cursor when you pause at the end of a line in the Edit view. On the Mac, ⌥⇥ or → accepts it and Esc dismisses it; ⌥Esc or F5 asks for one without waiting.

The suggestion is not part of your note until you accept it. It is drawn on screen and nothing more — it cannot reach a save, a search result, your links or a Git diff.

On iPhone and iPad, tap the suggestion to accept it — or press ⌥⇥ with a keyboard attached; Esc dismisses it. Suggestions come from the model chosen in Settings ▸ AI. They are off until you turn on Suggest as I type, in the Inline Completion section of the AI settings.

Ask your library

Ask Your Library answers questions using your own notes as the source. It finds the relevant ones, reads them, and answers with its sources listed beneath — the notes it drew on — so you can check the reasoning and jump to the original.

It is most useful for questions you know you have written about but cannot place — “what did I decide about the pricing model?” rather than general knowledge. Open it from Ask Your Library at the top of the sidebar, or with View ▸ Ask Your Library (⇧⌘J); it opens as a tab beside your notes. On iPhone it is in the Notes and AI tabs.

The Assistant

The Assistant is a conversation about your collection, with tools: it can search your collection, read notes, propose edits and search the web. Open it from Assistant at the top of the sidebar, or with View ▸ Assistant (⇧⌘A). It opens as a tab beside your notes rather than a window, so a note and the Assistant are a tab apart. It looks at your notes before it answers a question about them, and says what it is doing while it works — searching your notes, reading a note, waiting for your approval. The wrench and screwdriver button at the top turns its tools off, for a conversation that neither reads nor changes your notes.

Changes wait for your approval. When the Assistant wants to change a note, it shows you the exact change first and waits; nothing is written until you approve it. If you choose Allow all this session, the rest of that conversation’s changes are made without asking — except deleting a note, which always asks. In a collection that is a Git repository, each change you approve is committed straight away as a commit of its own — that note and nothing else, whatever Auto-commit is set to — so it can be taken back on its own. No commit is made where Auto-commit is never allowed: in a cloud folder, or when the collection is one folder of a larger repository.

If it proposes several changes at once, they wait their turn, one card at a time. A change is made only to the text you approved: if the note was edited while the card was waiting, the Assistant is told to read it again instead. Skills hold reusable instructions for repeated jobs — a note named SKILL.md, with a name: and a description: in its front matter — and the Assistant loads the one a request matches.

On a model with a window of at least 16,000 tokens — in this version, an MLX model on a Mac — the Assistant can also read whole web pages and run deep research, a longer multi-step investigation across your notes and the web. With a smaller window it searches the web and works from the results. The model it is using is always shown at the top of its tab.

Choosing a model

Settings ▸ AI has one choice, for everything the app does with AI — the Assistant, the research behind New Note from a Prompt, Summarise, Suggest Tags and Links, Rewrite, Compose, Ask Your Library and the suggestions as you type. It can be:

  • System — Apple’s model on your device, whichever one Apple Intelligence runs on your hardware. The name is Apple’s own. The default.
  • MLX · model name — an open model from your models folder, run on your device. Every model in the folder that HelloNotes can run is listed here, one entry each, so choosing a model and choosing MLX are the same act. A folder with nothing runnable in it leaves the picker offering System — and, if MLX was your choice, a line saying the folder has no model.

Under the picker is what the model is used for, one line saying where your text goes, one saying what a web search sends — for a model that can use tools — and, if it can’t run right now, why not.

Under Assistant are the model’s own settings, as the Foundation Models framework has them and no further: Creativity (0–2) and Sampling — Automatic, Greedy, Top-k (which adds Words to sample from) or Top-p (which adds Probability), the last two also offering a Seed so a run can be repeated — plus a Maximum reply length and, on a model that reasons, Thinking. They apply to the Assistant; each writing tool asks for what its own task needs.

This is the AI tab of Settings, the same on every device. Settings opens with ⌘, or the gear in the bar over the note; on iPhone, from the ⋯ in the Notes tab. It is the only AI settings screen: the Assistant’s gear button and every AI Settings… button open Settings on this page.

Open models with MLX

HelloNotes suggests no models. Choosing one is the advanced end of the app: a recommended list is a generation out of date within months, and whether a model is any good at your work is between you and the model.

MLX models live in one place, the models folder. Until you say otherwise that is HelloNotes’ own storage.

On a Mac your models are probably already here, in the Hugging Face cache ~/.cache/huggingface/hub that mlx_lm and the other MLX tools share — but macOS keeps HelloNotes out of that folder until you allow it. Access MLX Models… opens it, and one click on Open allows it for good: everything in it HelloNotes can run is listed, and downloads join it rather than making a second copy of a multi-gigabyte model. Change… points the folder somewhere else afterwards. On iPhone and iPad the button is Choose Folder…, for a folder in Files or on an external drive.

  • Use a model in the folder, or Remove… it. Removing deletes it from the folder, for every tool that shares it, so HelloNotes asks first.
  • Download an MLX language model from Hugging Face by typing its name in the form organisation/model. It goes into the models folder, and a download can be cancelled. The settings link through to the mlx-community organisation, which converts most models to MLX.
  • If Hugging Face isn’t reachable where you are, put a model into the models folder another way. Once a model is on your device it works offline.

One MLX model runs at a time, so the one you pick is the one everything uses: the Assistant and the writing tools share it. Pick it in the Model picker, or with Use beside it in the models list — they are the same choice.

Not every open model can use tools — Gemma 3, for one, has no way to be shown them. With such a model the AI settings say so, the Assistant chats without reading or changing your notes, and Research isn’t available; the writing tools work as usual. HelloNotes also says when a model’s weights are large for the device it is on.

How much a model can read

Every model has a window — how much text it can hold at once. HelloNotes asks Apple Intelligence how large the System model’s window is rather than assuming one. An MLX model is given 16,384 tokens on a Mac and 8,192 on iPhone and iPad, because a larger window costs memory. Text in Chinese, Japanese or Korean takes about a token a character, so the same window holds fewer characters of it.

  • A long note is summarised whole — in parts, then the parts — rather than by its opening. One too long even for that is refused, not cut short.
  • Rewrite asks for a shorter passage if a selection is more than the model can rewrite in one go, instead of rewriting only the part that fits and replacing all of it.
  • Tags and links read a note’s opening if it is very long — they are suggestions — and tags come back in the note’s own language.