Jiawei Zhang

lean4. Lean 4 programming language and theorem prover

Claude-of-Duty. A Call of Duty-quality FPS in Three.js, built from a single prompt.

i3dgs. Official Implementation of SIGGRAPH'26 paper "Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency"

blender-web. C++

ez-tree. Procedural tree generator written with JavaScript and Three.js

ApexForge. 一款开箱即用的AI 3D可视化建模平台，支持扩展和二次开发

scroll-world. A skill that turn any brand into a scrollable 3D world

streets-gl. 🗺 OpenStreetMap 3D renderer powered by WebGL2

Three.js-Object-Sculptor-Codex-Plugin. Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.

box3d. Box3D is a 3D physics engine for games

Three.js-Claude-Skill-Package. 24 deterministic skills for Three.js 3D web development with Claude Code. Covers WebGL, WebGPU, React Three Fiber, Drei, physics, IFC, and more.

webgpu-claude-skill. A Claude skill for developing WebGPU applications with Three.js

threejs-game-skills. Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.

threejs-skills.

open-terminal. A computer you can curl ⚡

speech-to-speech. Build local voice agents with open-source models

StreamSplat. [ICLR 2026] StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams

meshflow. Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

Lift4D. Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild

ArtiFixer. Python

pixelfy. Pixelfy is an open-source application that uses AI to generate stunning pixel art images for your creative projects.

aseprite. Animated sprite editor & pixel art tool (Windows, macOS, Linux)

pixelit. Create pixel art from an image

godot-demo-projects. Demonstration and Template Projects

intellij-community. IntelliJ IDEA & IntelliJ Platform

world-tracing. Office inference code for World Tracing (object/scene/dynamic). Live demos: https://haoz19.github.io/world-tracing-page/

thicket. Thicket: Laubwerk Plants Add-on for Blender

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

manim. Animation engine for explanatory math videos

TripoSplat. TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.

codegraph. Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

tixl. TiXL is an open source software to create realtime motion graphics.

RiGS. Implementation of paper "RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video"(CVPRF)

Fusion360GalleryDataset. Data, tools, and documentation of the Fusion 360 Gallery Dataset

Claude-Code-Game-Studios. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

editor. Browser-based visual editor for building WebGL, WebGPU, WebXR apps

awesome-metaverse. Awesome metaverse projects

hyperfy. World building for everyone

webglstudio.js. A full open source 3D graphics editor in the browser, with scene editor, coding pad, graph editor, virtual file system, and many features more.

chili3d. A browser-based 3D CAD application for online model design and editing

3DAIGC-API. Scalable 3D generative AI backend, with a collection of popular 3D AIGC models (ImageTo3D, TextTo3D, AutoRig, Mesh Segmentation, Mesh Painting, Mesh Editing etc.), all ported to API-ready services. Ready-to-use docker available.

kokraf. Collaborative 3D Modeling Application on the Web

aholo-viewer. A high performance 3DGS renderer

ide. ✨ Simple, free and open-source online code editor.

monaco-editor. A browser based code editor

editor. Create and share 3D architectural projects.

mesh-splatting. Python

mesh2splat. Fast mesh to 3D gaussian splat conversion

cell-architecture-studio. Interactive 3D cell architecture gallery built with React and Three.js

xterm.js. A terminal for the web

End-to-End-3D-Reconstruction-Paper-List. multi-view, end2end, 3D Reconstruction

blender-mcp. Open-source MCP to use Blender with any LLM

articraft. Superseded by https://github.com/articraftresearch/Articraft. This repository is kept for reference.

openreel-video. OpenReel Video - Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no installation, no cloud uploads, no watermarks.

freecut. FreeCut is a professional-grade video editor that runs entirely in your browser. Professional video editing, zero installation. Create stunning videos with multi-track editing, keyframe animations, real-time preview, and high-quality exports.

video-use. Edit videos with coding agents

SpatialLM. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

folio-2025. JavaScript

my-room-in-3d. JavaScript

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Code-as-Room. A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.

openpencil. The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.

skills. Skills for Real Engineers. Straight from my .agents directory.

Direct3D-S2. [NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

lingbot-map. A feed-forward 3D foundation model for reconstructing scenes from streaming data

Pixal3D. [SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

index-tts. An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

fastmap. A fast and simple structure from motion pipeline written in Pytorch.

image-blaster. An image-to-world skillset for Claude.

map-anything. MapAnything: Universal Feed-Forward Metric 3D Reconstruction

World-R1. [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Flow4DGS-SLAM. Official Implementation of the CVPR 2026 Highlight paper "Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM".

openaccess.

godot-mcp. MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output.

Vibe3DScene. Create your own 3D scene with words anywhere.

claude-code-sourcemap. TypeScript

Claude-Code. 可运行的Claude Code源码

claude-code. Claude Code Source - Buildable Research Fork. Reverse-engineered build system, runnable with Bun.

claude-reviews-claude. Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

spark. :sparkles: An advanced 3D Gaussian Splatting renderer for THREE.js

museum-of-all-things. a nearly infinite 3d museum, dynamically generated from wikipedia

hermes-agent. The agent that grows with you

bilarf. Code Release for "Bilateral Guided Radiance Field Processing"

dn-splatter. DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

SPAG4d. Convert 360° equirectangular panoramas into viewable 3D Gaussian Splat files.

daVinci-MagiHuman. Python

DROID-W. [CVPR 2026] DROID-SLAM in the Wild

inspatio-world. Python

paperclip. The open-source app everyone uses to manage agents at work

gstack. Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

rembg. Rembg is a tool to remove images background

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

ACE-Step-1.5. The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

YuE. YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

LTX-2. Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

heartlib. HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

model-viewer. 3D Model Viewer supporting glTF and 3D Gaussian Splats

draco. Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.

o3de. Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations.

godot. Godot Engine – Multi-platform 2D and 3D game engine

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

LoGeR. Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

OpenAIglasses_for_Navigation. a open framework for blind navigation based on esp32

MASt3R-SLAM. [CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Gaussian-SLAM. Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

MonoGS. [CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

SplaTAM. SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

CloudCompare. CloudCompare main repository

frontend-slides. Create beautiful slides on the web using a coding agent's frontend skills

I-Scene-project. spatial intelligence; interactive 3D scene generation; world model; real-to-sim

XScene-UEPlugin. A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.

FAST_LIO. A computationally efficient and robust LiDAR-inertial odometry (LIO) package

LOD-3DGS. LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian(Published in SIGGRAPH Asia 2024)

InfiniDepth. [CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

shannon. Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

GPU-Grants. GPUGrants - a list of GPU grants that I can think of

speedy-splat. Python

HY-WorldPlay. HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

GaussianEditor. [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

ShapeR. Code for the ShapeR research paper

Comfyui_TTP_Toolset. for tile the image for advanced control or modification

ComfyUI-qwenmultiangle. A ComfyUI custom node for 3D camera angle control. Provides an interactive Three.js viewport to adjust camera angles and outputs formatted prompt strings for multi-angle image generation.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

photogrammetry_datasets. Collection of 350+ datasets for photogrammetry

VGGT4D. The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”

Qwen-Image-Layered. Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

supersplat. 3D Gaussian Splat Editor

splat-transform. CLI tool and library for 3D Gaussian splat processing and conversion

engine. Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF

spz. File format for 3D Gaussian splats. About 10x smaller than the PLY equivalent with virtually no perceptible loss in visual quality. Offered as open source by Niantic Labs. More details at https://scaniverse.com/spz #3dgaussiansplats #gaussiansplatting

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

MetalSplatter. Render Gaussian Splats using Metal on Apple platforms (iOS/iPhone/iPad, macOS, and visionOS)

browser-sharp. JavaScript

ml-sharp. Sharp Monocular View Synthesis in Less Than a Second

KernelAgent. Autonomous GPU Kernel Generation & Optimization via Deep Agents

WorldGen. 🌍 WorldGen - Generate Any 3D Scene in Seconds

FastVGGT. [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer

croco. Python

RoboSimGS. Code for [RA-L] High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting

TTT3R. [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

CUT3R. Official implementation of Continuous 3D Perception Model with Persistent State

DeepSeek-R1.

DeepSeek-V3. Python

HunyuanVideo-I2V. HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

HunyuanWorld-Mirror. [ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

LLFF. Code release for Local Light Field Fusion at SIGGRAPH 2019

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

FlashWorld. Code for "FlashWorld: High-quality 3D Scene Generation within Seconds" (ICLR 2026 Oral)

seeed-voicecard. 2 Mic Hat, 4 Mic Array, 6-Mic Circular Array Kit, and 4-Mic Linear Array Kit for Raspberry Pi

usb_4_mic_array. ReSpeaker 4 Mic Array with builtin VAD, DOA, AEC, Beamforming & NS

x393. mirror of https://git.elphel.com/Elphel/x393

Framework-Laptop-13. Documentation for the Mainboard and other modules in the Framework Laptop 13

FourThirdsEye. Open source Raspberry Pi 5 compatible Micro Four Thirds camera module based on IMX294

OneInchEye. A One Inch CMOS sensor (IMX283) camera board designed for Raspberry Pi

ov9281-camera-board. Camera board with a pair of OmniVision OV9281 sensors

caliscope. Multicamera Calibration for Motion Capture Workflows

USB_C_Industrial_Camera_FPGA_USB3. Source and Documentation files for USB C Industrial Camera Project, This repo contains PCB boards, FPGA , Camera and USB along with FPGA Firmware and USB Controller Firmware source.

odas. ODAS: Open embeddeD Audition System

16SoundsUSB. 16 Synchronized Inputs USB (UAC2) Sound Card Based on XMOS xCORE-200

lib_xua. XMOS USB Audio

omi. AI that sees your screen, listens to your conversations and tells you what to do

OpenGlass. Turn any glasses into AI-powered smart glasses

MentraOS. MentraOS is the leading smart glasses OS. See live captions, stream your view, talk to AI, and capture photos hands-free on compatible glasses.

QDarkStyleSheet. A dark style sheet for QtWidgets application

PyQt-Fluent-Widgets. A fluent design widgets library based on C++ Qt/PyQt/PySide. Make Qt Great Again.

qt-material. Material inspired stylesheet for PySide2, PySide6, PyQt5 and PyQt6

qt-material-widgets. :art: Qt widgets-based implementation of the Material Design specification.

PyQtDarkTheme. A flat dark theme for PySide and PyQt.

Modern_GUI_PyDracula_PySide6_or_PyQt6. Python

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

360-gaussian-splatting. This repository contains programs for reconstructing 3D space using OpenSfM and Gaussian Splatting techniques. It allows users to generate point clouds from images captured by a 360-degree camera using OpenSfM, and then train Gaussian Splatting models using the generated point clouds.

Relativty. An open source VR headset with SteamVR supports for $200

360-camera-metadata. This repository exists to accumulate and understand file formats and metadata standards generated by 360 cameras.

3dgs-render-blender-addon. 3DGS Render by KIRI Engine

blender. Official mirror of Blender

kdenlive. Free and open source video editor, based on MLT Framework and KDE Frameworks

openshot-qt. OpenShot Video Editor is an award-winning free and open-source video editor for Linux, Mac, and Windows, and is dedicated to delivering high quality video editing and animation solutions to the world.

multinerf. A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

OpenSourceSmartGlasses. Open Source smart glasses designed to be 1. All day wearable 2. Immediately useful 3. Extendable for makers, startups, and everyone else.

4d-gaussian-splatting. [ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

3d-gaussian-splatting. Implementation for 3d gaussian splatting

viser. Web-based 3D visualization in Python

UnityGaussianSplatting. Toy Gaussian Splatting visualization in Unity

GaussianSplats3D. Three.js-based implementation of 3D Gaussian splatting

splat. WebGL 3D Gaussian Splat Viewer

gsplat. CUDA accelerated rasterization of gaussian splatting

pyroomacoustics. Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

ambisonic-encoding. Example MATLAB/Octave scripts to perform ambisonic encoding of microphone array signals

360GS. Official code for "360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roaming"