jhj0517

oai-skills. The contents of /home/oai/skills in ChatGPT's code interpreter environment

ml-agents. The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

Wan-Alpha. [CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel

Lucy-Edit-ComfyUI. Python

AP2. Building a Secure and Interoperable Future for AI-Driven Payments.

VibeVoice. VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

VibeVoice. Open-Source Frontier Voice AI

InfiniteTalk. ​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

MVVM-Architecture-Android. MVVM architecture using Kotlin, Dagger, Retrofit, Coroutines, Flow, StateFlow, and etc.

ComfyUI-FramePackWrapper. Python

FramePack. Lets make video diffusion practical!

MapleStory-node-resources. MapleStory node Resources Wz extractor and server

auto-maple. Artificial intelligence for MapleStory that uses machine learning and computer vision to navigate challenging in-game environments

manifest-android-interview. 🚀 Manifest Android Interview is the ultimate guide to cracking Android technical interviews.

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

MSDWILD. [INTERSPEECH 2022] This dataset is designed for multi-modal speaker diarization and lip-speech synchronization in the wild.

SegAnyMo. [CVPR 2025] Code for Segment Any Motion in Videos

prometheus-fastapi-instrumentator. Instrument your FastAPI with Prometheus metrics.

subwer. Python

KAI-Scheduler. KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale

whatsapp-mcp. WhatsApp MCP server

komodo. 🦎 a tool to build and deploy software on many servers 🦎

firebase-mcp. 🔥 Model Context Protocol (MCP) server for Firebase.

mcp-installer. An MCP server that installs other MCP servers for you

dify-mcp-client. MCP Client as an Agent Strategy Plugin. Support GUI operation via UI-TARS-SDK.

mcp-cli. Python

ollama-mcp-bridge. Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

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

firecrawl-mcp-server. 🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

pyppeteer. Headless chrome/chromium automation library (unofficial port of puppeteer)

browser. Lightpanda: the headless browser designed for AI and automation

docs. Documentation for ComfyUI

AudioX. [ICLR 2026] Repository of AudioX

feedparser. Parse feeds in Python

python-sdk. The official Python SDK for Model Context Protocol servers and clients

ComfyUI-backend. Python

ComfyUI-MultiGPU. This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose

diffusion-self-distillation. [CVPR 2025] Diffusion Self-Distillation for Zero-Shot Customized Image Generation

compose-effects. 🧵 Compose Effects enable you to launch efficient side-effects without unnecessary operations for Android and Compose Multiplatform.

Spark-TTS. Spark-TTS Inference Code

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

gson. A Java serialization/deserialization library to convert Java Objects into JSON and back

mox. modern full-featured open source secure mail server for low-maintenance self-hosted email

Moop-Android. 🚧🚧🚧 WIP 🚧🚧🚧 한국 멀티플렉스 극장의 현재상영작, 개봉예정작 정보를 모아 보여주는 안드로이드 앱입니다.

Awesome_Resume_Portfolio. 개발자를 위한 이력서 작성 가이드, 포맷 그리고 다양한 예시들

novelai-bot. Generate images by NovelAI | 基于 NovelAI 的画图机器人

Sonic. Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

flutter_silero_vad. This is an unofficial plugin for calling the Silero VAD ONNX model in Flutter.

ComfyUI-WanVideoWrapper. Python

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

speech_to_text. A Flutter plugin that exposes device specific text to speech recognition capability.

MegaParse. File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

Step-Video-T2V. Python

open-health. OpenHealth, AI Health Assistant | Powered by Your Data

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

pippo. Pippo: High-Resolution Multi-View Humans from a Single Image

SwapCudaVersionWindows. How to swap/switch CUDA versions on Windows

Zonos. Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

ComfyUI-workflows. Personal Collection of ComfyUI Basic workflows

spring-boot. Spring Boot helps you to create Spring-powered, production-grade applications and services with absolute minimum fuss.

ComfyUI_PuLID_Flux_ll. Python

goose. an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

aws-saa-c03. Comprehensive collection of my personal study notes and resources for the AWS Certified Solutions Architect - Associate (SAA-C03) Exam. Aimed to aid anyone on their journey to becoming an AWS Certified Solutions Architect.

groovy. Python

hibiki. Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.

open-with-cursor-context-menu. Add "Open with Cursor" to your context menu for files, folders, and background areas.

ComfyUI-PuLID-Flux. PuLID-Flux ComfyUI implementation

PuLID. [NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

onnxruntime_flutter. A flutter plugin for OnnxRuntime provides an easy, flexible, and fast Dart API to integrate Onnx models in flutter apps across mobile and desktop platforms.

sherpa-onnx. Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

ComfyUI-Crystools. A powerful set of tools for ComfyUI

smolGPT. Python

sd-scripts. Python

ComfyUI_examples. Examples of ComfyUI workflows

AI.Tech. Trends, Tools, News timeline ...

F5-TTS. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

slink. Self-hosted image sharing service

github-drama. Collection of heated/controversial github discussions

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

X-Codec-2.0. Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

DeepSpeed-Kernels. C++

LLaSA_training. LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

local-llasa-tts. Examples of using the llasa-tts models locally

PdfDing. Selfhosted PDF manager, viewer and editor offering a seamless user experience on multiple devices.

Android-MVVM-Architecture-Android-Voice-AI-SDK. Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin

finetuning-notebooks. Jupyter Notebook

leapfusion-hunyuan-image2video. A novel approach to hunyuan image-to-video sampling

ComfyUI-jhj-Kokoro-Onnx. ComfyUI wrapper for Kokoro (TTS) models

diffusion-pipe. A pipeline parallel training script for diffusion models.

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

lighthouse. Automated auditing, performance metrics, and best practices for the web.

flutter_sticky_header. Flutter implementation of sticky headers for sliver

remote-or-flexible-work-company-in-korea. 한국에서 원격근무 혹은 자율출퇴근이 되는 회사 리스트를 아카이브합니다

flash-attention. Fast and memory-efficient exact attention

dejavu. Audio fingerprinting and recognition in Python

kokoro-onnx. TTS with kokoro and onnx runtime

CleanArchitectureForAndroid. Clean Architecture for Android - a sample project

gitdiagram. Free, simple, fast interactive diagrams for any GitHub repository

kafka. Apache Kafka - A distributed event streaming platform

nestjs-aop. A way to gracefully apply AOP to nestjs

WebToon. Android 웹툰 Application

ComfyUI-MMAudio. Python

frontend-fundamentals. Essential principles for frontend development

prometheus. The Prometheus monitoring system and time series database.

interactive-artwork. TypeScript

ComfyUI-Moondream-Gaze-Detection. ComfyUI wrapper for Moondream's gaze detection

kimptracker-swagger-ui. kimptracker OpenAPI doucmentation using swagger ui

TransPixeler. CVPR2025

noticon. a icon library for notion

gaze-detection-video. Use the Moondream 2 model to detect faces and their gaze directions in videos.

moondream. tiny vision language model

nats-server. High-Performance server for NATS.io, the cloud and edge native messaging system.

MultiModuleGradleManagement. Kotlin

n8n. Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

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.

BGE-M3-Model-Converter. A tool for manual conversion of BGE-M3 models with preserved trainable variables and direct control over model outputs.

closetalk.app. App Template | Android, Kotlin, Jetpack Compose, Jetpack Navigation, feature modules, MVI, Koin, Coil, Proto DataStore, GitHub Actions

perse. [CVPR 2025] PERSE: Personalized 3D Generative Avatars from A Single Portrait

use-funnel. A powerful and safe step-by-step state management library at React

warehouse. The Python Package Index

Deathlog. Lua

TeaCache. Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

ComfyUI-AniDoc. ComfyUI Custom Nodes for "AniDoc: Animation Creation Made Easier". This approach automates line art video colorization using a novel model that aligns color information from references, ensures temporal consistency, and reduces manual effort in animation production.

Ruyi-Models. Python

SynCamMaster. [ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

ComfyUI-CustomNodes-Template. ComfyUI CustomNode Template

video-watermark-removal. Remove simple watermarks from videos with minimal setup

CodeUpdateArena. Python

AnkiAIUtils. AI-powered tools to enhance Anki flashcards with explanations, mnemonics, illustrations, and adaptive learning for medical school and beyond

MisguidedAttention. A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information

FaceLift. [ICCV 2025] FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

ComfyUI-Florence2. Inference Microsoft Florence2 VLM

ComfyUI-AnimateDiff-Evolved. Improved AnimateDiff for ComfyUI and Advanced Sampling Support

ComfyUI-Advanced-ControlNet. ControlNet scheduling and masking nodes with sliding context support

ghostty. 👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

NAIToolbar. NAI Toolbar Chrome Extension

wasm-vips. libvips for the browser and Node.js, compiled to WebAssembly with Emscripten.

termo. Termo is a simple terminal emulator for the browser. It is a wrapper on top of xterm

openauth. ▦ Universal, standards-based auth provider.

waifu2x_snowshell. Multilingual waifu2x GUI shell for windows x64

comfyui-profiler. Calculate the execution time of all nodes.

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

rembg. Rembg is a tool to remove images background

backgroundremover. Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.

video2x. A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

velog-client. TypeScript

diffused-texture-addon. Generate Diffuse Textures on Meshes directly in Blender 3D with Stable Diffusion.

Tech-Interview.

p2pool. Decentralized pool for Monero mining

malware-ioc. Indicators of Compromises (IOC) of our various investigations

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

vid2densepose. Convert your videos to densepose and use it on MagicAnimate

magic-animate. [CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

ComfyUI-HunyuanVideoWrapper. Python

HelloMeme. The official HelloMeme GitHub site

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

wesql. WeSQL is an innovative MySQL distribution that adopts a compute-storage separation architecture, with storage backed by S3 (and S3-compatible systems). It can run on any cloud, ensuring no vendor lock-in.

my-star-dev-list. 내 마음대로 정하는 스타 개발자 리스트

Kiwi. Kiwi(지능형 한국어 형태소 분석기)

cuda_bitcoin_miner. CUDA Based GPU Bitcoin Miner

cpuminer. CPU miner for Litecoin and Bitcoin

js-gpu-bitcoin-miner. Mines bitcoin in the browser using WebGL to compute the hashes and a server to negotiate the stratum mining protocol and coordinate clients.

secret_miner. Miner(cpu or gpu) for bitcoin, secretly run in a period of time

Soul-of-Waifu. 🌌 Give a soul to your favorite characters. Soul of Waifu is a desktop roleplay & AI companion app featuring Live2D/VRM avatars, voice chat & local LLM. Evolve together across immersive chat, RPG adventures, and your desktop.

AI_Girlfriend. Creating a waifu

fastapi-nginx-gunicorn. Example app for article

locust. Write scalable load tests in plain Python 🚗💨

DanceFusion. JavaScript

stock-price-forecasting. ResNLS: an improved model for stock price forecasting.

Galformer-Improved-Transformer-for-Time-Series-Prediction. Galformer: A Transformer with Generative Decoding and a Hybrid Loss Function for Multi-Step Stock Market Index Prediction

llm-twin-course. 🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

ComfyUI-LTXVideo. LTX-Video Support for ComfyUI

OpenMG. WvsGlobal fork targeted for v22

JoyVASA. Diffusion-based Portrait and Animal Animation

edge-tts. Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

alphafold3. AlphaFold 3 inference pipeline.

bounce_tapper. Smooth touch animations with Shrink/Grow effects, easily enhancing user touch interaction.

three_point_three. 삼쩜삼앱에 토스 터처 인터렉션 끼얹기

Music-Source-Separation-Training. Repository for training models for music source separation.

LLaMA-Mesh. Unifying 3D Mesh Generation with Language Models

murmurai. 🎙️ Drop-in replacement for paid transcription APIs. Self-hosted, GPU-powered, speaker diarization. Free forever: uvx murmurai

krita-ai-diffusion. Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

masoori. SSAFY 9기 특화프로젝트 대전_3반_B308 - Masoori

ComfyUI-YOLO. ComfyUI-YOLO: Ultralytics-Powered Object Recognition for ComfyUI

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

espnet. End-to-End Speech Processing Toolkit

text-behind-tost. Python

SolPic-client. Sol.Pic(Solve Picture)은 수학문제 이미지를 AI를 활용해 풀이과정과 정답을 제공해주는 모바일기반 어플리케이션 입니다.

Fllama. A flutter binding for llama.cpp, which use platform channel.

website. The website / "start here" for the project. This project has been abandoned and merged into the open source Raccoons Rise Up game.

UnityTutorials-RTS. The code for my series of tutorials on how to make a real-time stategy (RTS) game in the well-know Unity game engine (with C# scripting)!

ProjectTemplate-Python. Python Project Template

Real-ESRGAN. PyTorch implementation of Real-ESRGAN model

SwinIR. SwinIR: Image Restoration Using Swin Transformer (official repository)

DimensionX. [ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

X-Portrait2. X-Portrait 2

InstantIR. InstantIR: Blind Image Restoration with Instant Generative Reference 🔥

gradio-range-slider. Svelte