Starred repositories
A music composer and song learning webapp made for the games Genshin and Sky Cotl. Made with Next.js, WebMIDI, WebAudio, pixi.js
Reverse engineer anything with agents, from app behavior down to native binaries.
3rd-person character controller with Gaussian splats, Rapier physics, and Three.js.
G-code generator for Snapmaker U1 with Full Spectrum layer blending
JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System
A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Gro…
Official source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.
UNITRONIX / UniCAD
Forked from FreeCAD/FreeCADOfficial source code of FreeCAD, a free and opensource multiplatform 3D parametric modeler.
a open framework for blind navigation based on esp32
Fara1.5 – A family of frontier computer use agent models
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
[IJCV 2025] Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
MimiClaw: Personal Agent on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS. On device Muse.
原神、星穹铁道、绝区零、实时双语字幕-视频字幕提取-支线配音插件 Real-time OCR-based subtitle matching and translation tool for anime-style games
PyTorch code and models for the DINOv2 self-supervised learning method.
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching