I'm a CS student at Nanjing University of Posts and Telecommunications, heading to Soochow University for an AI Master's this September.
I build things at the intersection of computer vision, natural language processing, and interactive systems. Currently obsessed with AI agents and how they can enhance real-world workflows.
| Project | Description | Tech |
|---|---|---|
| Echoesphere | My graduation project — an experimental interactive game where sound shapes the world |   |
| echoesphere_agent | AI decision-making agent for exhibition contexts |  |
| echoesphere-communication | Raspberry Pi sensor data collection & LED strip control |  |
| perry_hermes | A vibe-coded AI agent in Rust |  |
| amagicpear.github.io | My personal homepage |  |
Languages: Python · C# · Rust · TypeScript · C++
Frameworks: Unity · Svelte · Tauri · MediaPipe · LangChain
AI/ML: Computer Vision · NLP · LLM Agents · Gesture Recognition
Design: Blender · Visual Design
Music: Ableton Live · Acoustic Guitar
Infra: Raspberry Pi · TCP Socket · WebAssembly · Docker
- Building AI agents that actually work in production
- Exploring multimodal interaction systems (vision + language + hardware)
- Learning Rust for systems-level performance
- Making LLM-powered tools that simplify real-world workflows
"The best code is the code that doesn't exist — but if it must exist, make it minimal."
I'm not trying to write the most code. I'm trying to write the least code that does the most. Every refactor, every optimization, every architectural decision starts with one question: can this be simpler?
Built with ❤️ and minimal lines of code