Marker: a 39k-star open-source tool converting PDF/DOCX/PPTX to Markdown and JSON with high accuracy
Shruti_0810 · x · 2026-08-24
Marker is Datalab's open-source document intelligence project that converts PDF, image, PPTX, DOCX, XLSX, HTML, and EPUB files into Markdown, JSON, chunks, and HTML quickly and accurately. It handles tables, forms, equations, inline math, links, and code blocks in all languages, extracts and saves images, removes headers/footers and artifacts, supports custom formatting logic, optionally boosts accuracy with LLMs, and runs on GPU, CPU, or MPS. The repo has 39k GitHub stars.
Related event: Open-Source Marker v2 Parses 23.7 Pages per Second on a B200 GPU(2 posts)→
More from coding & agent
- LangChain answers the most common questions about agent evals: datasets, judges, and trajectories — LangChain · 2026-10-16
- Signal65 benchmarks: Intel Xeon 6 runs agent workloads 11% faster for less money — ryanshrout · 2026-10-16
- Vercel Daemons in production: log delivery pipeline hits 1 Gbit per second and ramping — cramforce · 2026-10-16
- From Mathematica to ~1000 Python scripts: a 20-year math visualization journey — S_Conradi · 2026-10-16
- How to Get Better at Delegating to Your AI Assistant: It's a Learnable Skill — craigsdennis · 2026-10-16
- HeyGen MCP turns ChatGPT recipes into personalized cooking videos — toolstelegraph · 2026-10-16