A ThreeJs module to quickly setup a Media Pipe skeletal rig with minimal code.

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

Quickstart bash script for AMD RyzenClaw and RadeonClaw

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches…

Code of Strips as Tokens: Artist Mesh Generation with Native UV Segmentation. ACM Transactions on Graphics (SIGGRAPH 2026)

Lightweight toolkit to debloat, install APKs, and customize Android TV devices.

Fast and accurate AI powered file content types detection

Desktop app to download videos, courses. YouTube, Instagram, TikTok, Bilibili (哔哩哔哩), Douyin (抖音), 小红书, 快手, 优酷, Hotmart, Udemy, Kiwify, Telegram, and 1000+ more via yt-dlp. Download torrents and s…

Autonomous Hacking Agent for Red Team Testing

The agent that grows with you

Text-to-audio and video-to-audio using Sony AI's Woosh foundation model.

Public release of the Sound Effect Foundation model by Sony AI.

World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

Standalone client for managing official builds of Blender 3D and its popular forks

OBS Studio - Free and open source software for live streaming and screen recording

ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, th…

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

The Smallest English TTS Model with only 1M parameters

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

Powerful and extensible proxy server with anti-censorship functionality for Android

LLAMA Turboquant implementation with CUDA support

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

ComfyUI pack for RAW, noise and EXIF manipulations

Custom GeForce Now Client Named OpenNOW

VoxCPM2 TTS for ComfyUI. 30 languages, voice design, controllable cloning, 48kHz audio, and LoRA training