Skip to content

NameetP/pdfmux

Developer Productivity

Self‑healing PDF extractor that audits each page, re‑extracts failures and supports OCR, table, LLM fallback backends for clean RAG input

Track releases GitHub Website
Python Latest v1.8.5 · 59m ago Security brief →

Features

  • Per‑page confidence scoring and automatic self‑audit of extraction quality
  • Routed extraction through multiple rule‑based backends (PyMuPDF, OpenDataLoader, RapidOCR, Docling, Surya, Marker) plus BYOK LLM fallback
  • Zero‑config CLI and Python API with chunking, schema‑guided structured output, cost estimation and CI‑friendly strict mode

Recent releases

View all 19 releases →
No immediate action
v1.8.1 New feature

Verification audit tool

Open
No immediate action
v1.8.4 Bug fix

Version string fix

Open
No immediate action
v1.8.3 Bug fix

Dead link fix + timeout termination

Open
Config change
v1.7.0 Breaking risk
Breaking upgrade

--strict on by default

Open
No immediate action
v1.6.4 Breaking risk

audit command + upsell line

Open

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
75
Forks
12
Languages
Python JavaScript Shell
Downloads/week
7 ↑550%
NPM Maintainers
1 Single npm maintainer
Contributors
3
View on GitHub View on npm Homepage

Install & Platforms

Install via
pip

Similar tools

signaturepdf
bentopdf
PSPDFKit/nutrient-dws-mcp-server
olgasafonova/mediawiki-mcp-server
ndjordjevic/pinrag

Alternative to

LlamaParse

Beta — feedback welcome: [email protected]