From 4952771f99aa8c3d715783bd9c81718491b6cd49 Mon Sep 17 00:00:00 2001
From: Nameet Potnis <93118951+NameetP@users.noreply.github.com>
Date: Wed, 29 Apr 2026 16:23:02 +0400
Subject: [PATCH] Add pdfmux to Tools

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 11e2bb0..bfdb858 100644
--- a/README.md
+++ b/README.md
@@ -247,6 +247,10 @@ Processing: A Survey**
   *CocoIndex is an open-source ETL framework to index data for AI, such as RAG; with realtime incremental updates and support custom logic like lego.*  
   [`Website`](https://cocoindex.io/)
 
+- **pdfmux**  
+  *Open-source PDF extraction orchestrator. Routes each page to the best of 5 backends (PyMuPDF, OpenDataLoader, RapidOCR, Docling) with optional BYOK LLM fallback. Per-page confidence scoring catches and re-extracts failures with a stronger backend. Ranks #2 on opendataloader-bench (200 real-world PDFs). Built-in MCP server. Native LangChain + LlamaIndex loaders.*  
+  [`Website`](https://pdfmux.com) [`GitHub`](https://github.com/NameetP/pdfmux)
+
 ## Other Collections
 
 - [Awesome LLM RAG](https://github.com/jxzhangjhu/Awesome-LLM-RAG)