Search inside your files by meaning — 100% private

Filename search fails the moment you only remember what a document says. This tool reads your folder on your device and finds documents by their content — no uploads, no account, nothing to install.

How it works

1

Choose a folder

Point the app at any folder on your computer — contracts, research papers, meeting notes, a whole documents drive. It only ever asks to read, never to change anything, and nothing is uploaded.

2

It reads your documents on your device

PDFs, Word documents, Markdown, plain text, and code are read and understood right in your browser. You can start searching what's ready within seconds while the rest of a big folder streams in — and the app remembers what it read, so next time is instant.

3

Search by meaning

Type what you remember — “the contract with the termination clause”, “notes about the Berlin offsite budget” — and get ranked results with the exact matching passage highlighted, even when the document uses completely different words.

Search inside PDF files without uploading them

Every cloud “AI search” product asks you to upload the very files you least want to upload — contracts, medical records, financials. This tool searches inside PDF files, Word documents, and notes without a single byte leaving your computer.

Unlike your operating system's search, it matches meaning, not just keywords: “termination clause” finds “either party may end this agreement”, even with zero words in common. Every result shows the matching passage, its section or page, and can open the file right there.

Why it works offline

  • A one-time setup download teaches your browser to understand documents. It's saved on your device — from then on, no internet is needed and everything works offline.
  • Your files are read directly from your disk, and everything the app learns is stored in your browser on this device — there is no server to talk to.
  • Disconnect your internet to test: searching keeps working, because nothing about it ever needed the network.

Supported file types

PDF Text-based PDFs, read page by page (scanned-image PDFs are listed honestly as unreadable for now)
Word .docx and legacy .doc, with section headings preserved in results
PowerPoint & Excel .pptx slides and .xlsx sheets
Markdown & plain text .md, .txt, logs, CSV, and other text formats
Code JavaScript/TypeScript, Python, Go, Rust, Java, C/C++, SQL, and more

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.