🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

Lightweight coding agent that runs in your terminal

一键DD/重装脚本 (One-click reinstall OS on VPS)

A collection of GitHub Actions to accelerate your Gradle Builds on GitHub

🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。

CCTV m3u8 流畅稳定直播源

Tunnel all your traffic over Websocket or HTTP2 - Bypass firewalls/DPI - Static binary available

Laravel based app for filtering and editing IPTV provider playlists

电视节目

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

MCP Server for Ghidra

Awesome Digital Human

数字人资料整理

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

使用winsper语音识别开源模型封装成openai chatgpt兼容接口,高性能处理

Conversion between Traditional and Simplified Chinese

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

YOLOv12: Attention-Centric Real-Time Object Detectors

Build OpenSSL in parallel within CMake

Windows inside a Docker container.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Rediscover the beauty of typography.

A lightweight game engine written in modern C++

A beautiful stack trace pretty printer for C++

Header-only TOML config file parser and serializer for C++17.

header only, dependency-free deep learning framework in C++14

Create beautiful applications using Go

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

lightweight, standalone C++ inference engine for Google's Gemma models.