About this tool

html-to-markdown-ai converts documents into GitHub-Flavored Markdown that you can paste straight into an LLM context window or feed into a RAG pipeline. Drop HTML pages, PDFs, Word files, slides, spreadsheets, EPUBs or a whole website export as a folder or ZIP archive, and you get one Markdown file per document. Scanned PDFs can go through OCR (PaddleOCR models on ONNX Runtime Web), which also runs on your device.