OpenDataLoader open-sources a PDF-to-Markdown parser hitting 100 pages/sec on CPU
mdancho84 · x · 2026-11-05
A new open-source tool, OpenDataLoader PDF, parses PDFs into AI-ready data at up to 100 pages per second, running entirely on CPU. It's #1 on GitHub Trending with 30.2k stars.
Key details:
- Outputs: Markdown for RAG chunking, JSON with bounding boxes for source citations, and HTML; Python/Node.js/Java SDKs plus LangChain integration — three lines of code after pip install opendataloader-pdf.
- Accuracy: 0.907 overall and 0.928 table accuracy across 200 real-world PDFs (multi-column, scientific papers), ranking #1 in benchmarks; uses deterministic local mode plus an AI hybrid mode for complex pages.
- OCR: built-in 80+ language OCR in hybrid mode, works with poor-quality scans at 300 DPI+.
- Complex content: borderless tables, LaTeX formulas, and AI-generated chart descriptions.
- Apache 2.0, fully free, and can also automate PDF accessibility.
More from coding & agent
- Teardown: Viral Claude Code Skill Turns Any Machine Into a 3D Simulator You Can Take Apart — huangyun_122 · 2026-11-05
- Evals cheat sheet: a plain-language guide to knowing whether an AI system actually works — blaizedsouza · 2026-11-05
- Dataflare: open-source product analytics that runs in your own Cloudflare account — isnit0 · 2026-11-05
- App Store Connect CLI ships 39 releases in 60 days, hits 8.2k GitHub stars — rudrank · 2026-11-05
- Parcha open-sources Recall, the skill that became their company brain for Claude Code sessions — blaizedsouza · 2026-11-05
- tw93 open-sources Kami: a design system that makes AI-agent documents actually readable — sujingshen · 2026-11-05