I think in systems, build in code, and teach from the work.
I'm the founder and software architect behind Casys, based in Taiwan. I work where agent protocols, engineering models, business systems, data, and decision-making meet.
I like turning complicated real-world work into software that is executable, inspectable, and useful to the people who own it.
Casys · Open source · Field notes · Teaching · LinkedIn
- Agent infrastructure — MCP systems and operator surfaces that connect agents to the tools, permissions, knowledge, and traces behind real workflows.
- Engineering software — from system architecture to CAD and simulation, with evidence that carries into the wider workflow.
- Data, graphs, and optimisation — knowledge structures, exact models, heuristics, and interfaces that make difficult decisions legible.
understand → model → build → run → document → teach
I publish field notes, diagrams, and working examples alongside the code. Documentation is part of the product, and teaching is how I test whether the ideas remain useful outside the repository where they started.
Most of my open work lives at Casys-AI. These projects capture the range:
- mcp-server — the TypeScript foundation behind Casys MCP servers and apps.
- mcp-erpnext — agent-operated ERPNext workflows with interactive views.
- mcp-chrono — prescribed rigid-body kinematics with Project Chrono.
NutrientCompare is a transparent supplement comparison project built for Taiwan.
If you're building a system where an agent needs to do more than talk, say hello.