《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Deepfakes Software For All

Official Code for DragGAN (SIGGRAPH 2023)

JumpServer is an open-source Privileged Access Management (PAM) platform that provides DevOps and IT teams with on-demand and secure access to SSH, RDP, Kubernetes, Database and RemoteApp endpoints…

Contexts Optical Compression

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)

Janus-Series: Unified Multimodal Understanding and Generation Models

Source Han Sans | 思源黑体 | 思源黑體 | 思源黑體 香港 | 源ノ角ゴシック | 본고딕

StyleGAN - Official TensorFlow Implementation

Semantic Image Synthesis with SPADE

Nginx UI allows you to access and modify the nginx configurations files without cli.

A `.git` folder disclosure exploit

Install and config an OpenShift 3.x cluster

GitHub Action that uploads coverage to Codecov ☂️

Collect Windows Spotlight daily lockscreen.