docling-project/docling
- Source
- GitHub
- First trending
- Category
- Documents
- GitHub stars
- 67,053
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.

What it does
A document processing tool that parses formats including PDF and Office files. It represents layout, reading order, and table structure, exports formats such as Markdown and JSON, and supports local execution.
How it helps ATF
Company Brain can reference its structured document conversion before connecting company materials. LabChin can compare its parsing of research documents and tables.
License
MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.
More in this category
- dream-num/univer
An office SDK for embedding spreadsheets, documents, presentations, bases and boards in a product, with canvas rendering, a formula engine and one facade API for browser and Node.js. PDF is listed as coming soon. - lynote-ai/humanize-text
An open-source pipeline that rewrites AI-generated text into more natural prose. It runs two LLM rewrites at temperature 1.3, then two translation hops through different machine translation engines, and publishes every intermediate step. - aliyun/ai-agent-handbook
An open whitepaper on enterprise AI agents across architecture, build, run, governance and tuning, covering harness and model boundaries, context, state, tools, sandboxes, traces and evaluation, with a 2026 developer survey. - LaoFeng-mouse/flyingmouse-format
FlyingMouse Format is an offline Windows desktop app that converts images, documents, spreadsheets, slides, PDF, audio and video between formats, with OCR and batch conversion. It bundles FFmpeg, LibreOffice, Poppler and Tesseract. - chrisryugj/kordoc
A CLI and MCP server for converting Korean HWP and HWPX files, PDFs, and Office documents to Markdown. It also provides document comparison and automatic form filling.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.