Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

A real-time human motion tracking and analysis system optimized for Apple Silicon (M4), designed for precise posture correction, fitness training, dance coaching, and interactive body-based applica…

方糖全栈路线图2023，为「从螺丝钉到一人企业」补全技能栈

PyTorch实现高分遥感语义分割（地物分类）

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

📚 从零开始的大语言模型原理与实践教程

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Code release for DynamicTanh (DyT)

YOLOE: Real-Time Seeing Anything [ICCV 2025]

Solve Visual Understanding with Reinforced VLMs

Fully open reproduction of DeepSeek-R1

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

s1: Simple test-time scaling

OCR, layout analysis, reading order, table recognition in 90+ languages

【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析，按人类阅读顺序进行排序。

A Comprehensive Toolkit for High-Quality PDF Content Extraction

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

Image composition toolbox: everything you want to know about image composition or object insertion

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

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

UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

👾 Fast and simple video download library and CLI tool written in Go

Downloads videos and playlists from YouTube

🚀 Curated collection of Amazing Python scripts from Basics to Advance with automation task scripts.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.