PyPI98Exceptionalhealth index
Unstructured-IO/unstructuredConvert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
HTML★ 15.4K↓ 3.5M/moSep 16, 2026
npm · PyPI98Exceptionalhealth index
Python · TypeScript★ 45.2KSep 17, 2026
npm97Exceptionalhealth index
TypeScript · C++★ 1,765↓ 96.5K/moOct 17, 2026
PyPI94Exceptionalhealth index
krkn-chaos/krknChaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project.
Python★ 510Oct 19, 2026
PyPI94Exceptionalhealth index
Python★ 184.7K↓ 14.9M/moSep 16, 2026
PyPI94Exceptionalhealth index
mindee/doctrdocTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
Python★ 6,355↓ 235.7K/moSep 17, 2026
PyPI94Exceptionalhealth index
ocrmypdf/OCRmyPDFOCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Python★ 34.8K↓ 1.2M/moSep 16, 2026
PyPI · npm · Maven94Exceptionalhealth index
Java · Python★ 29.3K↓ 233.1K/moSep 16, 2026
npm · crates.io · PyPI94Exceptionalhealth index
Rust★ 12.9K↓ 1.2M/moOct 20, 2026
PyPI · npm93Exceptionalhealth index
PaddlePaddle/PaddleOCRTurn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Python · C++★ 89.6K↓ 125/moSep 16, 2026
PyPI93Exceptionalhealth index
RapidAI/RapidOCR📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
Python · Jupyter Notebook★ 7,851↓ 3.8M/moSep 17, 2026
crates.io · PyPI · npm +593Exceptionalhealth index
yfedoseev/pdf_oxideThe fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
Rust★ 1,015↓ 391.7K/moSep 5, 2026
npm92Excellenthealth index
PT-Perkasa-Pilar-Utama/ppu-paddle-ocrLightweight, probably the fastest PaddleOCR SDK in TypeScript. Multilingual Support. Runs anywhere JavaScript runs: Node.js, Bun, Deno, mobile react-native, web browsers, web worker, and browser extensions. Docker & CLI supported. The official SDK is browser-only.
TypeScript · HTML★ 134↓ 64.2K/moSep 15, 2026
npm92Excellenthealth index
TypeScript★ 26↓ 97.7K/moOct 6, 2026
npm · crates.io92Excellenthealth index
ruvnet/RuVectorRuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.
Rust · TypeScript★ 4,599↓ 489.6K/moOct 20, 2026
PyPI91Excellenthealth index
opendatalab/MinerUTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python★ 80K↓ 141.6K/moSep 16, 2026
Go91Excellenthealth index
y3owk1n/neruNavigate your entire screen without touching the mouse. [mac, linux, windows]
Go★ 680Sep 9, 2026
npm · crates.io90Excellenthealth index
SylphxAI/pdf-reader-mcpGive your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
TypeScript · Rust★ 933↓ 1,201/moSep 18, 2026
PyPI90Excellenthealth index
jztan/pdf-mcpAn MCP server that gives your AI agent agentic RAG over your PDFs, one file or a whole folder: hybrid semantic + keyword search, selective page reads, tables, images, OCR, chart data, and multi-column/CJK layouts. The agent decides when to search; pdf-mcp does the retrieval.
Python★ 134↓ 6,229/moSep 15, 2026
PyPI90Excellenthealth index
pymupdf/PyMuPDFPyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
Python · SWIG★ 10.6KAug 28, 2026
PyPI90Excellenthealth index
robocorp/rpaframeworkCollection of open-source libraries and tools for Robotic Process Automation (RPA), designed to be used with both Robot Framework and Python
Python★ 1,563↓ 748.4K/moSep 17, 2026
PyPI90Excellenthealth index
Python★ 61↓ 8.8M/moSep 17, 2026
PyPI · npm90Excellenthealth index
yusufkaraaslan/Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Python★ 15K↓ 22.1K/moSep 19, 2026
C · Rust★ 903Sep 15, 2026
PyPI89Excellenthealth index
CVHub520/X-AnyLabelingX-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export.
Python★ 10.7K↓ 2,623/moOct 15, 2026
NuGet88Excellenthealth index
C#★ 5Sep 13, 2026
PyPI · npm · crates.io87Excellenthealth index
firecrawl/pdf-inspectorFast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Rust★ 19.7K↓ 1.6M/moOct 20, 2026
npm · Packagist · crates.io +187Excellenthealth index
xberg-io/xbergPolyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence for 371 languages. Fifteen bindings, with CLI, REST API, and MCP server.
Rust★ 9,424↓ 2,541/moOct 18, 2026
NuGet · npm · PyPI86Excellenthealth index
EvotecIT/OfficeIMOMIT-licensed, COM-free .NET libraries for creating, reading, editing, converting, rendering, and extracting Office, PDF, email, OneNote, and text formats.
C#★ 544Sep 11, 2026
PyPI · npm86Excellenthealth index
Python · JavaScript · TypeScript★ 846↓ 11.2K/moSep 25, 2026