Local-first converter
PDF to Markdown for LLMs
Convert text-based PDFs into clean Markdown for ChatGPT, Claude, RAG, Obsidian, Notion, and GitHub workflows. Your file stays in your browser.
Browser workspace
Convert PDF to Markdown
Your PDF is processed locally in your browser. We do not upload or store your file.
Why convert PDF to Markdown for LLMs?
Markdown is easier to inspect, paste, chunk, and cite than raw PDF text.
How this converter works
PDF.js extracts embedded text in the browser, then a small formatter creates Markdown.
Where it fits
Use the output with ChatGPT, Claude, RAG pipelines, Obsidian, Notion, or GitHub.
Scenarios
One converter, multiple AI and note workflows
The first version focuses on readable text extraction. It does not promise OCR, perfect tables, or formula reconstruction.
Limits
Built for text-based PDFs first
- Scanned image PDFs need OCR before conversion.
- Complex tables, formulas, headers, footers, and columns may require cleanup.
- No uploaded PDF is sent to a server in this version.
FAQ
Questions before you convert
Is my PDF uploaded?
No. The converter reads the PDF in your browser and does not send the file to a server.
Can it handle scanned PDFs?
Not in v1. If the PDF is image-only, run OCR first and then convert the text-based result.
What Markdown format works best for LLMs?
Keep headings and page markers when you need citations. Use chunks when the document is too large for one prompt.