document-processing — salud del software de código abierto

crates.io · PyPI · npm +5

96Excepcionalíndice de salud

The 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★ 1089↓ 487K/mes21 oct 2026

Apache-2.021 oct 2026 · métricas 2.10.0

npm · crates.io · PyPI

94Excepcionalíndice de salud

run-llama/liteparse

A fast, helpful, and open-source document parser

Rust★ 12.9K↓ 1.2M/mes20 oct 2026

Apache-2.020 oct 2026 · métricas 2.10.0

npm

92Excelenteíndice de salud

PT-Perkasa-Pilar-Utama/ppu-paddle-ocr

Lightweight, 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/mes15 sept 2026

MIT15 sept 2026 · métricas 2.10.0

npm · crates.io

90Excelenteíndice de salud

SylphxAI/pdf-reader-mcp

Give 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↓ 1201/mes18 sept 2026

MIT18 sept 2026 · métricas 2.10.0

PyPI

90Excelenteíndice de salud

jztan/pdf-mcp

An 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↓ 6229/mes15 sept 2026

MIT15 sept 2026 · métricas 2.10.0

PyPI

90Excelenteíndice de salud

run-llama/llama-parse-py

Python SDK for OCR and document parsing in the cloud with LlamaParse

Python★ 61↓ 8.8M/mes17 sept 2026

MIT17 sept 2026 · métricas 2.10.0

crates.io · npm · PyPI +1

89Excelenteíndice de salud

yfedoseev/office_oxide

The fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.

Rust★ 154↓ 286K/mes20 oct 2026

Apache-2.020 oct 2026 · métricas 2.10.0

NuGet

86Excelenteíndice de salud

ShapeCrawler/ShapeCrawler

PowerPoint .NET library for reading, modifying, and generating PPTX presentations without Microsoft Office

C#★ 44110 sept 2026

MIT10 sept 2026 · métricas 2.10.0

PyPI

86Excelenteíndice de salud

oomol-lab/pdf-craft

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

Python★ 6314↓ 2560/mes19 sept 2026

MIT19 sept 2026 · métricas 2.10.0

npm

86Excelenteíndice de salud

run-llama/llama-parse-ts

Typescript SDK for OCR and document parsing in the cloud with LlamaParse

TypeScript★ 29↓ 285.2K/mes15 sept 2026

MIT15 sept 2026 · métricas 2.10.0

crates.io

84Excelenteíndice de salud

bzsanti/oxidizePdf

Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.

Rust★ 193↓ 36.6K/mes20 oct 2026

MIT20 oct 2026 · métricas 2.10.0

npm

81Excelenteíndice de salud

extend-hq/extend-typescript-sdk

An SDK to use the extend.ai API

TypeScript★ 6↓ 324.1K/mes11 sept 2026

MIT11 sept 2026 · métricas 2.10.0

PyPI

81Excelenteíndice de salud

shcherbak-ai/contextgem

ContextGem: Effortless LLM extraction from documents

Python · Jupyter Notebook★ 2003↓ 11K/mes20 sept 2026

Apache-2.020 sept 2026 · métricas 2.10.0

npm

80Excelenteíndice de salud

PSPDFKit-labs/nutrient-dws-client-typescript

This library provides a type-safe and ergonomic interface for document processing operations including conversion, merging, compression, watermarking, and text extraction using Nutrient DWS Processor API.

TypeScript★ 37↓ 6696/mes24 sept 2026

MIT24 sept 2026 · métricas 2.10.0

PyPI · npm

78Buenoíndice de salud

u9401066/asset-aware-mcp

Turn PDF, DOCX, tables, and figures into citation-ready reusable agent assets and Foam/LightRAG wikis — MCP SDK 2 server plus VS Code extension

Python · TypeScript★ 0↓ 677/mes12 sept 2026

Apache-2.012 sept 2026 · métricas 2.10.0

crates.io · npm · PyPI

77Buenoíndice de salud

wxyhgk/retain-pdf

在保留版面、公式与结构的前提下进行 PDF 翻译，适用于科研与技术文档

Python · Rust · TypeScript★ 229419 sept 2026

MIT19 sept 2026 · métricas 2.10.0

NuGet

75Buenoíndice de salud

iyulab/FileFlux

.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.

C#★ 520 oct 2026

MIT20 oct 2026 · métricas 2.10.0

Packagist · Go · crates.io +2

75Buenoíndice de salud

kreuzberg-dev/kreuzberg-lts

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

Rust · HTML★ 18↓ 2/mes20 oct 2026

MIT20 oct 2026 · métricas 2.10.0

crates.io

69Buenoíndice de salud

HyunjoJung/rwml

Native Rust Microsoft Word reader (.doc/.docx) + .docx writer + native PDF renderer — no JVM, panic-free, MIT

Rust · Python★ 2↓ 6051/mes17 oct 2026

MIT17 oct 2026 · métricas 2.10.0

npm · Go

67Buenoíndice de salud

giraffesyo/downmark

Fast, pure-Go document-to-Markdown conversion for PDFs, Office files, HTML, CSV, ZIPs, and text—available as a CLI and modular library.

Go★ 0↓ 1347/mes5 sept 2026

MIT5 sept 2026 · métricas 2.10.0

npm

63Moderadoíndice de salud

Heey-Global/deep-ocr-n8n

El repositorio no publica descripción.

TypeScript★ 0↓ 440/mes8 sept 2026

MIT8 sept 2026 · métricas 2.10.0

npm

62Moderadoíndice de salud

Sqhao-O/dsh-docs

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与离线 OCR

TypeScript · Python · JavaScript★ 13↓ 2003/mes18 sept 2026

MIT18 sept 2026 · métricas 2.10.0

crates.io

60Moderadoíndice de salud

clark-labs-inc/pdfsink-rs

Fast pure-Rust PDF extraction library and CLI by Clark Labs Inc. — 10–50x faster than pdfplumber for text, word, table, layout, image, and metadata extraction.

Rust · Python★ 24↓ 2255/mes16 oct 2026

MIT16 oct 2026 · métricas 2.10.0

60Moderadoíndice de salud

giraffesyo/pdf

Robust, zero-dependency PDF text extraction for Go, with positioned glyphs, reading- order reconstruction, and hardened parsing.

Go★ 05 sept 2026

MIT5 sept 2026 · métricas 2.10.0

npm · Go

59Moderadoíndice de salud

laiye-ai/adp-cli

The official Laiye ADP CLI and skill built for humans and agents. It enables agents to perform parsing, classification, extraction, validation on any type of documents with high accuracy.

Go★ 7↓ 98/mes12 sept 2026

Licencia propia12 sept 2026 · métricas 2.10.0

PyPI · npm

57Moderadoíndice de salud

complydoc/complydoc

Know your documents before they reach an LLM

Python · TypeScript★ 8↓ 2805/mes9 oct 2026

MIT9 oct 2026 · métricas 2.10.0

npm · PyPI

56Moderadoíndice de salud

linhut/document-ai-assistant

AI 公文智能优化助手 — 基于 GB/T 9704 标准的公文格式智能检测与优化桌面应用，可本地离线部署

Python · TypeScript · HTML★ 10719 sept 2026

MIT19 sept 2026 · métricas 2.10.0

npm

53Moderadoíndice de salud

xmutfyh/dsh-plugin-writing-guard

Scientific writing & document integrity guard for AI-assisted research — argument economy, deterministic integrity, safe Word editing. Local · Deterministic · Zero LLM.

JavaScript · TypeScript · Python★ 46↓ 3883/mes12 oct 2026

MIT12 oct 2026 · métricas 2.10.0

PyPI

48Débilíndice de salud

vorojar/Folio-OCR

Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。

Python · JavaScript · CSS★ 47319 sept 2026

MIT19 sept 2026 · métricas 2.10.0

npm

31En riesgoíndice de salud

mixpeek/connectors

Integration connectors for Mixpeek — modules and plug‑ins that bring Mixpeek’s contextual intelligence to third‑party ecosystems.

JavaScript★ 1↓ 4712/mes30 sept 2026

Sin licencia30 sept 2026 · métricas 2.10.0

#document-processing