npm · crates.io · PyPI
run-llama/liteparse
A fast, helpful, and open-source document parser
Apache-2.02026年8月22日 · 指标 2.10.0
全部标签
目录标签
#document-processing
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
16 条记录
crates.io · PyPI · npm +5
yfedoseev/pdf_oxide
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.
Apache-2.02026年9月5日 · 指标 2.10.0
npm
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, and browser extensions. Docker & CLI supported. The official SDK is browser-only.
MIT2026年8月1日 · 指标 2.10.0
PyPI
run-llama/llama-parse-py
Python SDK for OCR and document parsing in the cloud with LlamaParse
MIT2026年8月8日 · 指标 2.10.0
npm
run-llama/llama-parse-ts
Typescript SDK for OCR and document parsing in the cloud with LlamaParse
MIT2026年8月1日 · 指标 2.10.0
crates.io · PyPI · npm +1
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.
Apache-2.02026年8月22日 · 指标 2.10.0
crates.io
bzsanti/oxidizePdf
Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.
MIT2026年8月22日 · 指标 2.10.0
NuGet
ShapeCrawler/ShapeCrawler
PowerPoint .NET library for reading, modifying, and generating PPTX presentations without Microsoft Office
MIT2026年7月18日 · 指标 2.10.0
PyPI
jztan/pdf-mcp
An MCP server that lets Claude Code and other AI agents work through large PDFs without overflowing their context — search by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scanned text, even from multi-column and Japanese layouts.
MIT2026年8月1日 · 指标 2.10.0
PyPI · npm
u9401066/asset-aware-mcp
Asset-Aware MCP Server — AI Agent precisely accesses tables, figures, sections from PDFs + .docx round-trip editing (DFM) with 46 tools / 13 resources, segmentation export, layout overlay, OCR preprocessing, knowledge graph (LightRAG)
Apache-2.02026年7月22日 · 指标 2.10.0
NuGet
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.
MIT2026年8月29日 · 指标 2.10.0
npm · Go
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.
MIT2026年9月5日 · 指标 2.10.0
Packagist · Go · crates.io +2
kreuzberg-dev/kreuzberg-lts
Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.
MIT2026年8月22日 · 指标 2.10.0
npm
heey-global/deep-ocr-n8n
该仓库未发布描述。
MIT2026年7月15日 · 指标 2.10.0
npm · Go
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.
自定义许可证2026年7月22日 · 指标 2.10.0
Go
giraffesyo/pdf
Robust, zero-dependency PDF text extraction for Go, with positioned glyphs, reading- order reconstruction, and hardened parsing.
MIT2026年9月5日 · 指标 2.10.0