Multilingual Document Layout Parsing in a Single Vision-Language Model

Contexts Optical Compression

#1 Locally hosted web application that allows you to perform various operations on PDF files

Phoenix is a local chatbot that does not require internet access or a GPU. It is free and open-source.

Modern Django admin theme

Mirror of https://git.ffmpeg.org/ffmpeg.git

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Generic automation framework for acceptance testing and RPA

Yet another WebUI for Nginx

Redis GUI by Redis

JSON Web Token implementation in Python

🚀 Strapi is the leading open-source headless CMS. It’s 100% JavaScript/TypeScript, fully customizable, and developer-first.

check links in web documents or full websites

Speech Toolkit for Malaysian language, https://malaya-speech.readthedocs.io/

Create amazing custom iOS keyboards with Swift & SwiftUI.

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

Open-source platform to build and deploy AI agent workflows.

[CVPR 2024] Guided Slot Attention for Unsupervised Video Object Segmentation

Complete Two-Factor Authentication for Django providing the easiest integration into most Django projects.

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Build Python barcode QR code SDK with Dynamsoft Barcode Reader.

Translates Django models using a registration approach.

Simple, open source, lightweight and privacy-friendly web analytics alternative to Google Analytics.

media downloader and library for various sites.

A feature-rich command-line audio/video downloader

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

SmolVLM Action Recognition