- All languages
- ANTLR
- ASP.NET
- Arduino
- Assembly
- AutoIt
- Batchfile
- Berry
- Bikeshed
- C
- C#
- C++
- CMake
- CSS
- Clojure
- Cython
- Dart
- Eagle
- G-code
- GDScript
- GLSL
- Go
- HLSL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- KiCad Layout
- Kotlin
- Lua
- MATLAB
- MDX
- Makefile
- Mathematica
- Max
- Objective-C
- Objective-C++
- OpenSCAD
- PHP
- Pascal
- Perl
- Processing
- Python
- QML
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- SMT
- SWIG
- Scala
- ShaderLab
- Shell
- Solidity
- Svelte
- Swift
- TeX
- TypeScript
- VHDL
- Visual Basic
- Visual Basic .NET
- Vue
- nesC
Starred repositories
Intuitive and ergonomic 3D viewer built with Python & ModernGL. Features touchless gesture manipulation and dynamic off-axis motion parallax.
Interactive 3D hologram box creating realistic physical depth motion parallax using off-axis asymmetric frustum projection and webcam head tracking
Turn your screen into a window. Webcam head tracking and off-axis projection let you look into any photo, 3D model or splat. Runs entirely in your browser.
A screen that behaves like a window: head-tracked off-axis projection in the browser (Three.js + MediaPipe).
Turn your monitor into an interactive 3D living window with real-time webcam head tracking and off-axis asymmetric frustum projection.
Head-coupled perspective with a laptop webcam: iris tracking with MediaPipe, a One Euro filter and off-axis projection. Ibmec computer vision course project.
A real-time 3D head-tracking demo that creates a realistic "window into a virtual world" effect using your webcam. Built with Three.js and MediaPipe FaceMesh.
A curated collection of papers on portrait style transfer
Laser / engraver design and control software for everyone, written in Rust. Opens LightBurn projects. A rough-around-the-edges hobby project.
EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure — training, inference, and avatar refinement.
Reverse engineer any repo into it's original prompt
Curated tools, case studies and papers for reverse engineering websites, games, apps, binaries, firmware and protocols. Source-reviewed, English and Chinese.
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻。
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9
Capture iPhone LiDAR and photos, reconstruct editable Three.js rooms, and explore them in a browser.
Craft Anything: understand how any software works, and craft your own.
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
A local AI assistant that can see, hear, speak, browse the web, control your computer, and remember — built entirely in native C++, it is GPU agnostic with in-process implementation and privacy-saf…
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Local-first AI pose transformation studio. Transform identity photos using Codex CLI, Google Antigravity, or ComfyUI.
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
Photoreal Blender scenes from a one-paragraph brief, built by AI agents: image→3D props on fal, scripted layout, lighting, camera and grade.
MeshPilot: independent open-source Android client for your own MeshCentral server (not affiliated with the MeshCentral project). Signed APKs in Releases.