Show HN: Docx-to-Markdown – Eigenpal open-sources layout-aware Word to Markdown converter

Products·launched

Browser-based PDF to Markdown converter using heuristics, not LLMs

LiteDoc is a browser-based tool that converts PDFs to Markdown using layout heuristics and OCR, avoiding the cost and complexity of LLM-based APIs. It solves the problem of expensive multi-step pipelines for users who need clean Markdown from PDFs without running a local model or paying per page.

LiteDoc is a browser-based tool that converts PDFs to Markdown using layout heuristics and OCR, avoiding the cost and complexity of LLM-based APIs. It solves the problem of expensive multi-step pipelines for users who need clean Markdown from PDFs without running a local model or paying per page.

MarkOut is a free, open-source web app that extracts highlighted text from PDFs and exports it as clean Markdown, all client-side. It uses PDF.js for rendering, a custom YOLO26 model for highlight detection, and ONNX Runtime Web for inference, ensuring privacy. It solves the problem of manually copying highlighted text for note-taking or feeding into LLMs.

Products·launched

Browser extension converts PDFs to Markdown locally using WASM Python

A Chrome extension that runs Microsoft's MarkItDown Python library via Pyodide (WebAssembly) entirely in the browser to convert PDFs, Excels, and DOCX files to Markdown. It saves LLM tokens by reducing context window waste from hidden metadata, and keeps documents private since no cloud service is involved.

A Chrome extension that runs Microsoft's MarkItDown Python library via Pyodide (WebAssembly) entirely in the browser to convert PDFs, Excels, and DOCX files to Markdown. It saves LLM tokens by reducing context window waste from hidden metadata, and keeps documents private since no cloud service is involved.

Nebula is a PDF-to-Markdown conversion tool designed to handle difficult documents like complex tables, charts, scans, and mixed layouts. It uses LLMs to preserve meaning for downstream RAG applications. The creator is seeking challenging PDFs to test and improve the parser.

Products·launched

Mac app converts PDFs, Word docs, spreadsheets, and scanned images to Markdown

Markedly is a native macOS app that converts PDFs, Word docs, spreadsheets, and scanned images into clean Markdown. It solves the problem of manually cleaning up messy formatted text when pasting into Obsidian or AI tools. The app uses local processing with zero dependencies, and a recent update added a Finder right-click action and clipboard conversion.

Markedly is a native macOS app that converts PDFs, Word docs, spreadsheets, and scanned images into clean Markdown. It solves the problem of manually cleaning up messy formatted text when pasting into Obsidian or AI tools. The app uses local processing with zero dependencies, and a recent update added a Finder right-click action and clipboard conversion.