MarkItDown (Microsoft)
Leading#2 in Open sourcehigh confidence
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).Our read
Why it ranks #2
The highest-starred document-conversion project in this category at about 168.7k GitHub stars, with Microsoft stewardship and broad LLM-pipeline adoption.Here is the catch
prioritizes text conversion over faithful layout reconstruction
complex tables and multi-column PDFs can lose structure
not an editor, viewer or full document-management system
Does this well
simple output format designed for LLM consumption
handles many common document types behind one API
lightweight integration and strong project visibility
Pricing
Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.
Key features
PDF and Office-to-Markdown conversionImage OCR and metadata extractionAudio transcriptionCLI, Python API and plugin support
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).
- 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).
- 5marker (Datalab)Fast, high-quality PDF/EPUB/DOCX to Markdown conversion with tables, math, and images; a general-purpose favorite (~38k 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).