Skip to content
View aiexkwan's full-sized avatar

Block or report aiexkwan

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.

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
aiexkwan/README.md

👋 Hi there, I'm Alex Kwan (aiexkwan)

💻 Software Engineer | AI Systems Integrator | WMS Architect
📍 Based in Manchester, UK


🧠 About

我專注於 Web-based WMS(倉庫管理系統)AI/ML 整合製造業自動化
目前以 TypeScript + Next.js + Supabase + GraphQL 為核心,結合 AI Agent Orchestration圖譜記憶(Neo4j),打造可持續演進的 SaaS 生態。

  • 🔧 主導多個 TypeScript + Supabase 專案(SaaS 化、一體化設計)
  • 🧩 研究 MCP servers、AI memory agents、可觀測性與可視化 dashboard
  • 🧾 習慣以文件驅動(架構決策、RLS 策略、性能指標、測試策略)

🚀 Featured Projects

Project Description Tech Activity
web-pennine-wms 企業級 Web WMS(掃碼標籤、RLS、報表、卡片化 UI) TypeScript · Next.js · Supabase · GraphQL ⏱️ Active

🔎 更多專案(含私有倉庫):WMS SaaS、AI Agent 工具鏈、可視化分析卡片


🧰 Tech Stack

  • 前端:Next.js(App Router)、React、Tailwind、shadcn/ui
  • 後端:Supabase(Auth/RLS/Functions/Storage/Realtime)、Edge Functions
  • 資料:PostgreSQL、Row Level Security、GraphQL(Apollo + Codegen)
  • AI:RAG pipeline、Agent Orchestration(AutoGen / CrewAI / Graphiti MCP)、向量檢索
  • Dev:Docker、GitHub Actions、Playwright / Vitest

🧩 System Architecture (WMS)

graph TD
  A[Next.js App<br/>Cards / Dashboards] --> B[Apollo Client<br/>GraphQL]
  B --> C[Supabase GraphQL / REST]
  C --> D[(PostgreSQL)]
  C --> E[Supabase Auth<br/>RLS Policies]
  C --> F[Storage / Labels<br/>PDF / Images]
  D --> G[Views / Mat. Tables]
  A --> H[Edge Functions<br/>Webhooks / Printing]
  H --> I[Label Service<br/>QR / Barcodes]
  A --> J[Realtime Subscriptions]
  J --> C
  D --> K[Analytics Exports<br/>CSV / PDF / Excel]
Loading

🤖 AI Agent Orchestration (Memory-centric)

flowchart LR
  U[User / Ops] <---> UI[Next.js UI]
  UI --> AG[Agent Orchestrator<br/>AutoGen / CrewAI / Graphiti MCP]
  AG --> RAG[RAG Pipeline<br/>Embeddings / Chunking / Policies]
  RAG --> KB[(Supabase Vector DB<br/>Docs / SOP / Orders)]
  AG --> MEM[(Neo4j Memory Graph<br/>Episodes / Facts / Preferences)]
  AG --> SVC[Supabase Functions / Edge]
  SVC --> DB[(PostgreSQL)]
  AG --> OBS[Observability<br/>Logs / Metrics / Traces]
Loading

🌱 Learning & Research

  • RLS + user_metadata 權限模型與審計追蹤
  • Neo4j Memory Graph & Data Lineage
  • Automated RAG pipelines(索引、策略、Prompt 組件化)
  • MCP × Docker:Tool-as-a-Service 整合

📊 Stats


📫 Connect


✨ “Build systems that learn — and people who evolve.”

Popular repositories Loading

  1. aiexkwan aiexkwan Public

  2. agentpet agentpet Public

    Forked from ntd4996/agentpet

    A native macOS menu bar app with a desktop pet that monitors your AI coding agents (Claude Code, Codex, Gemini CLI) in real time.

    Swift

  3. TokenBar TokenBar Public

    Forked from Nanako0129/TokenBar

    AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tracks Claude Code, Codex, Cursor, OpenCode & 25+ agents locally.

    Swift