Make scanned PDFs searchable offline — and let your AI read them
Turn scanned PDFs and photos of pages into searchable, copy-pasteable PDFs on your own computer, then ask Claude what they say. No uploads, no Acrobat.
Free · no account · 3 free uses of every tool · also for Mac (Intel), Windows, Linux
A scanned PDF is just pictures of pages: you can’t search it, select a sentence or copy a number out of it. Online OCR sites want you to upload the file — not great for contracts, tax papers or medical letters — and Acrobat’s OCR is a subscription.
What you ask
Make every scanned PDF in my Documents/Scans folder searchable, then tell me which one is the lease and what it says about the deposit.
What happens
- ocr_pdf reads every page with OCR on your computer and saves name searchable.pdf — it looks exactly like the scan, but the text is searchable and selectable — plus name.txt with all the text.
- Claude reads the text files to find and answer what you asked.
- Have photos of pages instead? ocr_folder turns a folder of JPG/PNG/TIFF pages into one searchable PDF.
Languages: English, German, French, Spanish, Italian, Portuguese, Dutch and Polish. Works with PDFs from scanners and phone scanning apps. Claude can also read a short scan you attach to a chat directly; this is for files on your disk, long documents and whole folders.
Under the hood
OCR runs Rescribe (GPL-3.0), which embeds the Tesseract OCR engine (Apache-2.0), with Tesseract’s language models — official releases, checked by SHA-256. Unofficial wrapper — credit to both projects.
Set it up
In Claude Code: /plugin marketplace add https://guihub.cc/.claude-plugin/marketplace.json then /plugin install gui-hub@gui-hub — or install GUI Hub Essentials. Every tool works 3 times free; $9 once unlocks everything.
Try it now
Free download — use it 3 times free. $9 once unlocks everything. Prefer to ask your AI? GUI Hub also works as an MCP server for Claude, Cursor and others.