1.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
+6,665 stars
from 76,282 · score 8.80
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
8 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.tobymao / sqlglot
Python SQL Parser and Transpiler
+273 stars
from 9,470 · score 5.61
3.pdfminer / pdfminer.six
Community maintained fork of pdfminer - we fathom PDF
+55 stars
from 6,993 · score 4.03
4.Scony / godot-gdscript-toolkit
Independent set of GDScript tools - parser, linter, formatter, and more
+42 stars
from 1,580 · score 3.76
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.
+15 stars
from 1,146 · score 2.77
6.ValvePython / vdf
📜 Package for working with Valve's text and binary KeyValue format
+4 stars
from 210 · score 1.61
+3 stars
from 189 · score 1.39
8.dogoncouch / logdissect
CLI utility and Python module for analyzing log files and other data.
+1 stars
from 161 · score 0.69