name: "Zhongyue Lin (Leo) | 林中岳"
location: "China"
role: "Interdisciplinary AI Researcher & Agent Architect"
education:
degree: "Data Science & Analytics"
research_interests:
- "Institutional Design → AI Orchestration"
- "Behavioral Economics → Agent Decision-Making"
- "Political Science → Multi-Agent Governance"
- "Organization Theory → Agent Team Patterns"
current_focus:
writing: "Interdisciplinary AI Blog (CivAgent Series)"
building: "Multi-AI Collaboration Infrastructure"
creating: "xiaotie - Lightweight AI Agent Framework"
maintaining: "10+ Claude Code Open Source Skills"
researching: "Historical Polities as Agent Design Patterns"
languages: ["中文 (Native)", "English (Fluent)"]
philosophy: "5000 years of institutional wisdom → AI architecture" |
|
Interdisciplinary AI Researcher — I map patterns from political science, behavioral economics, and organizational theory onto AI multi-agent architectures. My CivAgent series demonstrates how 5,000 years of institutional design — from Tang Dynasty quality gates to Athenian distributed consensus — directly inform modern agent orchestration patterns.
Multi-AI Architect — I build systems that make 9+ AI providers (Claude, GPT, Gemini, DeepSeek, Kimi, Qwen...) collaborate as unified agent teams. From smart task routing to inter-agent communication pipelines.
Open Source Creator — I build and maintain the largest Claude Code Skills ecosystem with 10+ packages, and contribute to multi-AI collaboration infrastructure used by developers worldwide.
"History is not just the past — it is a living fossil of organizational wisdom." 历史不只是过去的事，它是组织智慧的活化石。
My research bridges humanities and social sciences with AI systems engineering:
| Discipline | Theory Source | AI Application | Blog Series |
|---|---|---|---|
| History | Tang 3-Department System, Persian Satrapies | Quality gates, eventual consistency | CivAgent |
| Political Science | 57 polities, 6 governance modes | Multi-agent orchestration patterns | CivAgent |
| Behavioral Economics | Kahneman's Dual-System Theory | Fast/slow agent routing, bias mitigation | Standalone |
| Organization Theory | Simon's Bounded Rationality | Satisficing strategies, near-decomposability | Standalone |
|
57-Civilization → 6 AI Orchestration Modes 57 种政体 → 6 种 AI 编排模式
Key Mappings:
|
Multi-AI Collaboration Infrastructure 多 AI 协作基础设施
My Contributions:
|
||||||||||||||
|
Lightweight AI Agent Framework 轻量级 AI Agent 框架
Key Features:
|
The Largest Claude Skills Ecosystem 最大的 Claude Code 技能生态
|
||||||||||||||
|
Multi-AI Desktop Platform 智能多 AI 协作桌面平台
|
AI Usage Stats for macOS macOS AI 使用统计工具
|
| Essay | Discipline | Key Insight |
|---|---|---|
| Dual-System Theory and AI Agents | Behavioral Economics | Kahneman's System 1/2 → fast/slow agent routing, cognitive biases as failure modes |
| Herbert Simon and AI Agent Design | Organization Theory | Bounded rationality, satisficing, near-decomposability → agent architecture |
Mapping 5,000 years of political institutions to AI multi-agent architectures — 57 polities, 6 orchestration modes.
| # | Essay | History | AI Pattern |
|---|---|---|---|
| 1 | Why AI Orchestration Needs History | 5000 years of polities | Design pattern library |
| 2 | Six Orchestration Modes | 57 political systems | 6 agent topologies |
| 3 | Tang Dynasty Three Departments | Draft → Review → Execute | Pipeline quality gates |
| 4 | Ming Dynasty Dual-Track | Inner Court vs Outer Court | N-version programming |
| 5 | Athenian Democracy | Ecclesia + Boule + Dikasteria | Distributed knowledge aggregation |
| 6 | Persian Satrapies | 23 satrapies + Royal Road | Eventual consistency protocols |
| 7 | Theory Bridge & Implementation | Cross-disciplinary synthesis | Full architecture blueprint |
"Thinking, fast and slow — the same duality that governs human cognition should govern AI agent architectures." — inspired by Daniel Kahneman
快与慢的思考——支配人类认知的同一种二元性，也应当支配 AI 智能体的架构设计。
If you find my projects useful, consider giving them a star!
如果觉得我的项目有用，请给个 Star 支持一下！