Human parsing model for fashion and virtual try-on applications

[ICLR 2026] "Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals"

Native Multimodal Models are World Learners

A command-line tool to select default applications for document types and URL schemes on Mac OS X

A MLX port of FLUX and other state of the art diffusion image models based on the Huggingface Diffusers implementation.

OpenAI Plugins

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Menu bar manager for macOS 26

pyright fork with various type checking improvements, improved vscode support and pylance features built into the language server

MLX: An array framework for Apple silicon

A Mac utility that automatically downloads macOS Firmwares / Installers.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

These are commands I use with agents, mostly Claude

Python package for Korean natural language processing.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Machine Learning Systems

Persist Alpine.js state in the URL query string with browser history support

The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS

CADAM is the open source text-to-CAD web application

Keep Codex running forever

EloquentJS monorepo — Laravel Eloquent for Node.js

S3 ninja emulates the Amazon S3 API for developement and test purposes

Diagram-as-code for AWS architecture.

Replace port numbers with stable .localhost URLs for local development — built with Rust, only 1MB

Manage your dotfiles across multiple diverse machines, securely.

아래한글 hwp viewer and editor by rust and wasm

A CLI tool to switch and manage Codex accounts

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

A search (cmd+k) modal, for the Django admin UI, that searches your entire site.