the fastest PDF parser on the planet and it runs entirely on CPU.
• 100 pages/second conversion to clean Markdown
• Handles complex tables, nested layouts & tricky docs
• Built-in OCR for 80+ languages (hybrid mode)
• Official LangChain integration
• #1 on every PDF-to-Markdown benchmark
• Beats Docling (15x slower) and Marker (GPU + 1000x slower)
• Built with the PDF Association & veraPDF team
GitHub - opendataloader-project/opendataloader-pdf: PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. · GitHubhttps://github.com/opendataloader-project/opendataloader-pdf