Lei Sun — AI Engineering / Platform Engineering
I build AI engineering systems, platform tooling, developer tools, and fintech validation workflows. Say hello to Firefly, my 3D conversational avatar that follows your gaze and talks with you.
Articles (English)
- When AX Can’t Be Trusted: How to Keep Your AI Operating macOSSeptember 18, 2026
- agent-httpd: Taking AI All the Way Down to CSeptember 16, 2026
- spring-abac: An ABAC Microservice WalkthroughSeptember 12, 2026
- tsm-hub: Bringing LLMs, Tools, MCPs, and Skills into One Unified GatewaySeptember 11, 2026
- Sprite Desktop Floating Widget: Folding System Monitoring, Pomodoro, and a Pocket AI into One Always-On PanelSeptember 9, 2026
- From Java to AI Agents, I’ve Always Been a BuilderSeptember 5, 2026
- An Agent Runtime Built on Spring AI Alibaba: Five Real Engineering Problems and Trade-offsSeptember 5, 2026
- Vibe Coding: I Read Less and Less of the Code AI Writes Line by Line — But I Still Rely on Docs to Understand ItSeptember 2, 2026
- firefly-studio Architecture Retrospective: Why a Desktop Digital Human Was Electron + C++ From Day OneSeptember 1, 2026
- Building a Local AI Chat Assistant from Scratch with React + TypeScript + Ollama: Streaming, Multimodal, and Production-Grade TestingAugust 28, 2026
- Cordis Plugin-Based Agent Runtime: Using a DI Container to Make LLM Backends, Tools, and Approval Flows All ConfigurableAugust 28, 2026
- From Chat UI to Agent Workbench: How the Interaction Layer of a Terminal Coding Agent UpgradedAugust 28, 2026
- 51 Indicators × 5000 Stocks: Engineering Practices for Full-Market Technical ScanningAugust 23, 2026
- If It Can Be Computed, Never Call a Model: The Deterministic Fast Path Runtime of resolve-harnessAugust 23, 2026
- SpecPulse: An Electron + React + Vite Workbench That Turns Natural Language into a Declarative UI Spec and Compiles It into Real React Components with Live PreviewAugust 19, 2026
- Evolution of a Distributed Order System: How Spring Boot + React Survived High Concurrency from a MonolithAugust 19, 2026
- cicdkit Engineering Practice: A Local CI/CD Single-Binary Platform Built with Pure Go Standard LibraryAugust 17, 2026
- Text2SQL Deterministic Pipeline + ReAct Dual-Path: Architecture Breakdown of datapulse AI BI WorkbenchAugust 16, 2026
- Purely Local Read-Only Video Indexing: blake3 Content Deduplication and Range Preview, How I Never Modify a Single Original FileAugust 14, 2026
- Local-First Markdown Indexing: From Zero-Dependency Rust to Read-Only Security Design ChoicesAugust 13, 2026
- Local Photo Indexing: 4 Design Decisions That Turn a File Pile into a Queryable DatasetAugust 12, 2026
- From SQLite to LLM Reranking: Seven Design Decisions for a Rust RAG ServiceAugust 10, 2026
- AutoGen PSE Architecture Deep Dive: Building Reliable Multi-Agent Collaboration with the Planner/Specialist/Evaluator PatternAugust 9, 2026
- From RBAC Authentication to a Small Microservice System: Spring Cloud + Zero-Dependency JWT + CRM + Audit + BFFAugust 7, 2026
- Building a Conversational 3D Avatar with React Three Fiber — Real Architecture and Deployment LessonsAugust 5, 2026
- Local-First AI Contacts Assistant: Bringing the LLM into Your Address Book Without Letting Data Leave HomeJuly 30, 2026
- Not Trusting the Executor: Verification Architecture for a Desktop AI WorkbenchJuly 29, 2026
- Preventing Agents from Lying at the Source: Building a RAG-Grounded PSE Multi-Agent Framework with LlamaIndex WorkflowJuly 11, 2026
- LangGraph PSE: Explicitly Modeling PSE Tri-role Collaboration with State MachinesJuly 9, 2026
- When LLMs Start Deceiving Themselves: A Multi-Agent Framework Guarding Article Credibility with Regular ExpressionsJuly 7, 2026