Grape
Semantic search for researchers

Find it by meaning, not by memory.

Describe an argument the way you remember it and the right note comes back. No naming convention to keep up with across a literature review, and no scrolling through interviews and field notes you filed months ago.
Meaning based search across everything you have ever written
Exact matches still work when you know the term
Narrow down by folder, tag or date when you know where to look
The same search on desktop and on your phone

No naming convention to keep up

Your filing can be a mess. Search reads what the note is about.

Best match first

Results are ranked by how close they are to what you described.

Folders and tags when you want them

Structure helps, it is just no longer the only way back to a note.

Indexed as you type

A note is findable by meaning the moment you stop writing it.

The same search on your phone

The thing you half remember is one tap away from the note list.

The agent searches the same way

Chat finds the right notes with it before it writes you an answer.
Findings

Three problems this addresses

Stated plainly, without the usual claims. What changes when the library can answer a question.
01
You annotated the paper last year and are reading it again.

Stop rereading papers you already annotated

Ask what your notes say about a method and get the answer with the note it came from, ready to cite.
02
The interview sits as audio for a month before anyone transcribes it.

Turn interviews into text the same day

Record the session, get a transcript in the note, and code it while it is still fresh.
03
The argument is spread across a year of files that never met.

See how the threads connect

Link notes to each other and use the graph view to spot the argument forming across a year of reading.
In practice

What that looks like for researchers

Three points in a project where the tool changes the work rather than decorating it.
01

Reading a new paper

Drop the PDF into a note, write alongside it, and tag it into the theme it belongs to.
02

Fieldwork day

Record on the phone, add photos, and let it all sync back to the desk copy.
03

Writing up

Ask for every note that touches a concept, then pull the quotes into the draft.
Questions

Questions Before You Install It

The rest of them live in the help center.
Can I keep sensitive research data off the cloud?
Yes. Grape is local first, so the database stays on your machine unless you turn sync on. If you need AI without sending text to a hosted provider, you can point Grape at a local model through Ollama or LM Studio.
Does it handle citations?
Grape is not a reference manager. It keeps your notes, PDFs and transcripts together and answers questions about them. Most researchers keep using Zotero or similar for bibliographies and use Grape for the thinking around them.
What is Grape, in one paragraph?
Grape is a note app for Mac, Windows, Linux, iPhone and Android with AI built into the middle of it rather than bolted on the side. You write, record and collect things the normal way, and then you can search by meaning, ask questions about your own notes, and turn any note into a summary, a set of flashcards, a quiz or a mind map.
What makes it different from other note apps?
Most note apps treat AI as an extra panel. In Grape the agent works on your workspace: it can read, create, edit, move, tag and delete notes, and every answer points back to the note it came from. Semantic search, voice transcription, flashcards, quizzes, mind maps and the drawing canvas all live inside the editor rather than in separate tools.
Where do my notes actually live?
On your device, in a local database, and you can choose where that file sits. Nothing needs to leave your machine for the app to work. If you turn on sync with a Pro plan, your notes are also stored in the cloud so your devices can stay in step.
Do I need an account to use it?
No. Download the app and start writing. You only need an account for the paid plans, which is where built in AI and cross device sync come in.

Ask what you already read.

Papers, interviews, field notes and half formed arguments in one local library you can question in plain language, months after you filed them.