Search inside your files by meaning

Point it at a folder and it reads every document in there (PDFs, Word files, notes, code) directly on your computer. Nothing gets uploaded, there's no account, and there's nothing to install. Type what a file says, not what it's named, and get ranked results with the exact matching passage highlighted.

What it can actually read

Only files it can pull real text from get indexed: everything else is either skipped outright or listed honestly as unread. Hidden files and folders (anything starting with a dot) are skipped automatically.

PDF Text-based PDFs, read page by page. A scanned PDF is a photo of a page, not text, so those come back listed as unreadable instead of silently dropped. There's no text recognition for scans yet.
Word .docx and legacy .doc, with section headings carried through into results.
PowerPoint & Excel .pptx slides and .xlsx sheets.
Markdown & plain text .md, .txt, logs, CSV, and similar text formats.
Code JavaScript/TypeScript, Python, Go, Rust, Java, C/C++, SQL, and more, split by function or class instead of an arbitrary character count.

How it works

1

Choose a folder

Point it at any folder (contracts, research papers, a whole notes vault). It only ever asks to read, never to change anything.

2

It reads what's inside

Text comes out of every supported file right there in the browser. You can start searching whatever's ready within seconds while the rest of a big folder is still being read, and it remembers what it's already read, so opening the same folder again only rereads what changed.

3

Search by what you remember

Type “the contract with the termination clause” and it finds “either party may end this agreement”, even with no words in common between the two.

Meaning search has a blind spot: here's how this one covers it

Rare, literal terms get a boost

Matching by meaning is good at finding a passage that says something similar in different words. It's worse at an invoice number, an error code, or a name typed exactly right. Those can get buried under a more generic-sounding result. So every candidate from the meaning-based ranking is also checked for exact word and phrase matches, with rarer query words counted for more than common ones. The two signals combine into one score, which is also where the highlighted text in each result comes from.

A short answer, if you turn it on

“Short answers” is off by default. Switch it on and, after your ranked results render, it drafts a two-to-three sentence answer built only from the passages you already see, with a clickable source next to each claim. It stays optional because it needs one more one-time download and a few extra seconds per question, and because the ranked passages are already the answer for most searches. When nothing retrieved actually supports an answer, it says nothing rather than guess.

One more effect of ranking by meaning: scores compress into a narrow band, so a middling result can look deceptively close to your best one on paper. Results that trail well behind the top match get tucked behind a “more distant matches” toggle instead of sitting at the top of the list.

Frequently Asked Questions

Is my data uploaded anywhere? +
No. Your files, your searches, and everything the app learns about your documents stay in your browser on your computer. The only download is a one-time setup that teaches your browser to understand documents; it's sizable but happens once, and after that you can disconnect your internet and searching keeps working.
Which browsers are supported? +
Chrome, Edge, and other Chromium-based browsers give the smoothest experience: they can remember your folder so return visits are one click. Firefox and Safari work too; you just choose the folder again when you come back, and because the app remembers what it already read, that takes seconds, not minutes.
What about scanned PDFs? +
A scanned PDF is a photo of a page, and this tool searches real text, so scanned pages can't be searched yet. They are listed honestly as unreadable rather than silently skipped, so you always know what was and wasn't searched. On-device text recognition for scans is planned.
How big can the folder be? +
Folders with thousands of documents work. The first read of a large folder can take a while, but you can start searching what's ready within seconds, and it only happens once. On later visits only new or changed files are read again, so the tool gets faster the more you use it.
Can other tools use what this app builds? +
Not yet, but an open export of the search index is planned, so other local tools and AI assistants on your computer will be able to reuse what this app has already read. The export will contain the text of your documents, so it should only be shared the way you'd share the documents themselves.