★ 60.5k stars

Docling parses PDFs, DOCX, and slides into structured text, preserving layout details like tables and headings for use in document processing agents.

Visit on GitHub ↗ docling-project/docling
GitHub repository github.com/docling-project/docling
Stars 60,536
Category Tools & Infrastructure

More in Tools & Infrastructure

Firecrawl ★ 125.7k

Firecrawl is a web scraping API that converts websites into clean, structured markdown, de…
Playwright ★ 89.7k

Playwright provides a single cross-language API to automate Chromium, Firefox, and WebKit …
LobeChat ★ 77.9k

LobeChat is an open-source AI chat framework that supports autonomous agent capabilities t…
AppFlowy ★ 71.4k

AppFlowy is an open-source alternative to Notion, licensed under AGPL-3.0, that provides a…
Unsloth ★ 65.3k

Unsloth is a library that fine-tunes large language models twice as fast while using 70% l…
Novu ★ 39.0k

Novu is a unified API and workflow engine that routes agent notifications across email, SM…