🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

real time face swap and one-click video deepfake with only a single image

Universal memory layer for AI Agents

one-click face swap

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

The Rogue Access Point Framework

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

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

Free and open-source map hosting solution with custom styles for websites and apps, using OpenStreetMap data

MemU is an open-source memory framework for AI companions

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…

MAESTRO is an AI-powered research application designed to streamline complex research tasks.

[NeurIPS'25 Spotlight] Official repository for "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment"

Amiri (أميري) is a body text Naskh typeface

Alfanous is an Arabic search engine API provides the simple and advanced search in Quran , more features and many interfaces...

scripts to detect ayah markers from quran images

A Madina Quran HTML Renderer without images

Morning and Evening Adhkar Database is an open-source project that provides structured data for morning and evening adhkar (supplications) in both Arabic and English. This project includes various …

AyahAi first automatic and easiest tool for splitting Quran images to ayahs with AI VER1.0

باحث قرآني مرن

Source code and test data of Pixelator v2

Font Awesome icons in SVG format