Stars
llama.cpp fork with additional SOTA quants and improved performance
High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
一款功能强大的可视化网页自动化工具，通过拖拽模块的方式快速构建自动化工作流，无需编写代码即可实现网页数据采集、表单填写、自动化测试等任务。
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Youtu-Tip: Tap for Intelligence, Keep on Device.
WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
High-performance vector search for Browser, Node, and Edge
LLMRouter: An Open-Source Library for LLM Routing
100% in-browser, hands-free AI voice chat using Whisper, WebLLM, and Supertonic TTS
Beautiful map components. 100% Free, Zero config, one command setup.
Qwen Image Integrated KSampler, intelligent multimodal sampler, support Z-Image, optimizes official offset issues, image scaling, multiple reference images, automatic VRAM/RAM management, batch gen…
We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.
MoCha: End-to-End Video Character Replacement without Structural Guidance
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
PersonaLive! : Expressive Portrait Image Animation for Live Streaming
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
支持用 Python 代码描述节点图，由内置引擎负责解析、验证、自动排版，再配合自动化脚本把步骤精准落到真实编辑器。
Native and Compact Structured Latents for 3D Generation