DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to pull text out of scanned PDF reports with Donsetch

Let DonSeTch fetch a scanned PDF and run its built-in OCR so the text can be read or searched.

  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Any agent

Authorization notice. Donsetch is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA research analyst or student who needs text from a scanned report, paper or filing found on the web.

The problemScanned PDFs contain no selectable text, so ordinary extraction returns nothing usable.

The outcomeThe agent returns the readable text of the scanned PDF, with OCR applied automatically.

What you need first

  • npm or Homebrew to install the binary
  • An MCP-capable client such as Claude Code or Cursor, or the standalone CLI
  • Network access to the sites you want to read
  • Optional: a Chromium, Playwright-cached Chromium or Edge build for tier-2 browser escalation

Steps

  1. Run npm install -g donsetch
  2. Run donsetch doctor to confirm the install
  3. Ask your MCP client to fetch the scanned PDF URL; the first OCR run downloads the models, about 37MB, then caches them
  4. Check the returned text against the PDF page you opened in a browser

Prompt for your agent

Using the donsetch MCP server, fetch the scanned PDF at <URL> and return its full text. Confirm the output contains readable sentences from the first page and state whether OCR ran.

Caveat. Prebuilt OCR is shipped for linux-x64, macOS and Windows; linux-arm64 is core-only, and fragile PDF handling on Linux ARM64 is listed as an honest limit.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page