marker (Datalab)
Leading#5 in Open sourcehigh confidence
Fast, high-quality PDF/EPUB/DOCX to Markdown conversion with tables, math, and images; a general-purpose favorite (~38k stars).Our read
Why it ranks #5
A popular conversion-focused project at about 37.8k GitHub stars, regularly included in 2026 PDF-to-Markdown comparisons for its accuracy and broad format support.Here is the catch
high-quality conversion can require substantial RAM or GPU resources
some advanced modes depend on external model services
not a general-purpose PDF editor
Does this well
high-quality structured output across varied documents
good table, math and image handling
usable locally with configurable models
Pricing
Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.
Key features
PDF, EPUB and Office conversionMarkdown, JSON and HTML outputTable, equation and image extractionOptional LLM-assisted cleanup
Sources we read
Quick facts
More in this area
The rest of the Open source column.- 1Stirling-PDFThe de-facto open-source PDF toolkit: 50+ local operations — merge, split, OCR, convert, sign, redact, compress — fully self-hosted. The recognized OSS PDF leader (~88k stars).
- 2MarkItDown (Microsoft)Microsoft's document-to-Markdown converter (PDF, Office, images, audio) built to feed clean text to LLMs; the highest-starred tool in this space (~169k stars).
- 3MinerU (OpenDataLab)High-accuracy PDF-to-Markdown/JSON extraction; the standout for complex academic papers and CJK layouts (~76k stars).
- 4Docling (IBM / DS4SD)IBM's document parser (PDF, DOCX, PPTX) with strong layout and table understanding; a default in the LlamaIndex/LangChain ecosystem (~64k stars).
- 6pdfplumberPrecise text, table, and layout extraction from born-digital PDFs; the go-to Python library for table scraping (~11k stars).
- 7PyMuPDFFast low-level PDF/XPS parsing, rendering, and editing (MuPDF bindings); the performance workhorse under many pipelines (~10k stars).