PDF2Markdown - Parse PDF and images to Markdown in seconds

I built PDF2Markdown because moving PDFs and scans into Markdown for RAG, docs pipelines, or AI agents was painful. Generic extraction tools often break on image-based PDFs, and maintaining custom parsers was costly. The approach: a single API that handles native PDFs, scanned images, and mixed documents, with layout-aware parsing and optional structured JSON. Then came the CLI and agent skills so AI coding tools like Cursor can convert PDFs directly when you say “convert this document.” It started with a few parsing backends, grew into sync and async modes, then SDK, CLI, and skills. The goal is making document ingestion as simple as a single API call or a phrase in your AI agent.