MD
MD Anything v1.0
Universal Document to Markdown Converter | Web PDF DOCX XLSX

Transform Any Document into Clean Markdown

Extract web pages, PDF reports, Word documents, and Excel spreadsheets into pure, structured Markdown for LLMs, RAG pipelines, and modern docs.

Playwright + BeautifulSoup PyPDF Layout Parser Python-Docx Styles Pandas Multi-sheet
Try sample: • •

Engineered for Precision & Developer Workflows

Built on specialized, battle-tested Python libraries designed for clean document conversion.

🌐

Web / URL → MD

Powered by Playwright and BeautifulSoup. Evaluates client-side JavaScript, discards boilerplate, and extracts semantic headings, lists, tables, and links.

playwright & bs4 engine
📑

PDF → MD

Powered by pypdf with layout mode parsing. Preserves pagination with page headers, author metadata, and collapses noisy hyphenation breaks.

pypdf layout extractor
📄

Word DOCX → MD

Powered by python-docx. Accurately maps heading levels (H1-H6), bold, italic, strikethrough, nested lists, embedded hyperlinks, and docx tables in order.

python-docx styles & tables
📊

Excel XLSX → MD

Powered by pandas and openpyxl. Iterates through all workbook sheets, handles NaNs, and transforms grids into clean GFM Markdown tables.

pandas multi-sheet tables
Developers

REST API Endpoints

Integrate markdown conversions into your LLM pipelines, RAG agents, or scripts.

Swagger UI ReDoc
POST /api/convert/url Convert webpage URL 
curl -X POST "http://localhost:8000/api/convert/url" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "use_playwright": true}'
POST /api/convert/file Universal File Upload (PDF, DOCX, XLSX, CSV) 
curl -X POST "http://localhost:8000/api/convert/file" \
  -F "file=@document.pdf"
GET /api/health Service Health Check 
curl -X GET "http://localhost:8000/api/health"