1.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
+21,541 stars
from 61,406 · score 9.98
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
7 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
2.tobymao / sqlglot
Python SQL Parser and Transpiler
+582 stars
from 9,161 · score 6.37
3.pdfminer / pdfminer.six
Community maintained fork of pdfminer - we fathom PDF
+120 stars
from 6,928 · score 4.80
4.Scony / godot-gdscript-toolkit
Independent set of GDScript tools - parser, linter, formatter, and more
+112 stars
from 1,510 · score 4.73
5.EmilStenstrom / justhtml
A pure Python HTML5 parser that just works. No C extensions to compile. No system dependencies to install. No complex API to learn.
+36 stars
from 1,125 · score 3.61
+9 stars
from 183 · score 2.30
7.ValvePython / vdf
📜 Package for working with Valve's text and binary KeyValue format
+8 stars
from 206 · score 2.20