Skip to content
View joyehuang's full-sized avatar

Highlights

  • Pro

Block or report joyehuang

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
joyehuang/README.md

Hi, I'm Joye 👋

I'm a Product Engineer based in Melbourne, studying Computing and Software Engineering at the University of Melbourne and spending much of my time building AI-powered products.

I don't really separate “how do we build this?” from “should we build this?” or “does this feel right to use?” I enjoy moving between those questions — from product decisions and agent architecture to interface design and the way a button responds. I care about software having a point of view, rather than feeling like another collection of features.

Writing is how I work through what I've learned, and community is where those ideas get challenged. Away from the screen, I play piano and cello, and take photos.

Currently

I'm turning the personal agent system I use for development, research, and everyday tasks into an installable, open-source Agent Harness. An initial installer is working in isolation; I'm still bringing the remaining workflows into the distribution before a public release. The goal is a long-term collaborator with memory, shared context, and useful judgment — not another disposable chat window.

My projects

  • Joye's Blog — My writing on agents, products, and lessons from building, with an interactive terminal to explore it.
  • Agent Skills — Reusable workflows for learning codebases, research, writing, and content creation.
  • MiniMind Notes — A hands-on guide to understanding LLMs through code and experiments.
  • Learn OpenHarness — An interactive guide to agent loops, tools, memory, and multi-agent systems.
  • Paperstrike — A hand-drawn browser FPS with solo arenas and a multiplayer lobby.

Products I've worked on

  • Atypica — A multi-agent platform for business and consumer research.
  • Playyy — An AI-powered image generation and brand design platform.
  • AIXCut — An AI video-editing agent.
  • fAIshion — An AI virtual try-on and outfit styling platform.

Bilibili · X · Xiaohongshu

Pinned Loading

  1. minimind-notes minimind-notes Public

    🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.

    Python 205 17

  2. skills skills Public

    HTML 9 3

  3. blog blog Public template

    joye's personal blog

    MDX 12 4

  4. Learn-Open-Harness Learn-Open-Harness Public

    🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程

    TypeScript 37 4