pdfllm
Local-first document intelligence

Turn complex PDFsinto source-linked Markdown

OCR, structure, tables and page-level citations in a clean document pack for Claude, Codex and Obsidian.

See how it works
Built for serious readingPrivate files stay in your browser by default
Product

A document pack, not a text dump.

PDFLLM rebuilds readable structure and keeps every exported block tied to its source page and PDF coordinates.

01

Structured Markdown

Headings, paragraphs and recoverable tables are separated into stable, editable blocks.

02

Traceable sources

Page links, anchors, bounding boxes, rotation and page dimensions travel with the document.

03

Portable output

Open the ZIP anywhere. No PDFLLM account or server is required to read the result.

Workflow

From PDF to usable context in three steps.

  1. Choose one PDFFiles up to 10 MB and 10 pages are processed in the browser.
  2. Review the mappingCompare the source page with its Markdown and inspect explicit quality flags.
  3. Take it anywhereDownload ZIP or Markdown, save a folder in Chromium, copy, or create an Obsidian note.
Quality

Uncertainty stays visible.

Local OCR and heuristic layout recovery can fail. PDFLLM surfaces uncertainty instead of silently pretending every conversion is perfect.

Low OCR confidenceEmpty scansGarbled textTable reconstructionMulti-column orderMissing page visuals
Pricing

Start locally. Upgrade securely.

Three successful conversions per account each month are free. Paid checkout is hosted by Waffo Pancake.

Local free$010 pages · 10 MB · 3 successful runs/month

Failed and cancelled conversions do not consume a run.

PDFLLM Pro$1.99 / month30 runs/month · 100 MB · 10 pages

Sign in to purchase. Checkout opens in a new tab.

Monthly subscription renews automatically until canceled. By continuing, you agree to the Terms and Refund Policy. Terms · Refunds