| Layer | Focus | Outcome |
|---|---|---|
| Product Systems | Agent workbenches, interaction design, operator workflows | Turn model capability into usable products |
| Execution Logic | Orchestration, automation, decomposition, tool use | Keep complex flows running reliably |
| Data Infrastructure | Crawling, cleaning, structuring, storage | Turn noisy input into reusable knowledge |
| Knowledge Layer | Knowledge graphs, academic profiling, entity modeling | Give systems long-term memory and usable context |
Most of my work sits across Python, TypeScript, and Dart, with a bias toward clean system boundaries and maintainable execution.
🧩 Meldwork |
🌐 Realm |
🔬 EvoLabeler |
🎓 Scholars-System |
🐱 Guameow |
🛰️ TDA-YOLO |
These panels show the contribution surface as a 3D map generated by github-profile-3d-contrib. The workflow runs daily and can also be triggered manually from GitHub Actions.
For a fuller view of my background, project context, and operating style:
If you are building AI products, agent systems, or knowledge infrastructure, or need to move a research-grade prototype into a working delivery, feel free to reach out.









