Stars
Lightweight deployment toolkit for Node.js and PM2 projects on your own servers.
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
Foadmin 是一款现代化的企业级后台管理系统，基于 Vue 3 和 Python FastAPI 构建。 我们致力于为开发者提供高效、灵活、易用的管理后台解决方案。
《动手学大模型Dive into LLMs》系列编程实践教程
JavaScript in-page GUI agent. Control web interfaces with natural language.
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Open Vision Agents by Stream. Build voice and 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…
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。
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
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. 🔥 🔥 🔥
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