Local AI Ocr
th1nhhdk
An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR AI (running directly on your machine).
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Find a skill for your next task. Preview examples where available.
Page 27 · 16 shown · 867 public entries
Results: 867
th1nhhdk
An local, offline (after initial setup), portable OCR software that can process images and PDF files, using DeepSeek-OCR AI (running directly on your machine).
ad-si
Over 1000 flashcards to learn Rust, SQLite, Lua, C, Godot, or Wolfram Language from first principles. Written in markdown with script to convert them to Anki decks or PD…
RapidAI
A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具,将复杂 PDF 文档转换为 Markdown 和 JSON 格式,使用onnx模型。
zouchenzhen
Codex / Claude Skill for editable thesis-defense PPTX from PDF or LaTeX while preserving a PowerPoint template. 从论文 PDF / LaTeX 生成可编辑答辩 PPTX,并保留指定 PPT 模板风格。
hyzyla
Typescript wrapper for the PDFium library, works in browser and node.js
sitewaerts
A Document Viewer cordova/phonegap plugin for iOS, Android and Windows
benjamin-awd
Monopoly is a Python library & CLI that converts bank statement PDFs to CSV.
bzsanti
Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.
Aymkdn
This module permits to convert HTML to the PDFMake format
kieranjwood
This code accompanies the the paper Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture (https://arxiv.org/pdf/2112.08534.pdf).
spawnia
A web service for converting markdown to PDF
svenssonaxel
A tool to sign PDF files. With Linux support.
PrinsFrank
PHP library to read and extract text & images from PDFs - Fast & Low memory - Built from scratch
jean-humann
Generate PDF for document website 🧑🔧
scambier
A (companion) plugin to facilitate the extraction of text from images (OCR) and PDFs.
opendatalab
A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.