Skip to content
View thundax-lyp's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report thundax-lyp

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
thundax-lyp/README.md

thundax

Building real-world systems and engineering workflows for reliable AI-agent collaboration.

Email thundax@qq.com Hugging Face thundax Profile views

Focus

Designing engineering environments where AI agents can work safely inside real codebases.

  • Repository-native protocols: documentation, task queues, tests, and Git history as stable collaboration interfaces.
  • Context routing: scoped docs that tell AI what to read, when to read it, and what not to read.
  • Architecture constraints: explicit module boundaries, naming rules, dependency direction, and quality gates.
  • Real-system validation: 0-to-1 AI-native backend design and legacy Java/Spring modernization.

Engineering Practice

  • Backend systems: Java, Spring Boot, Spring Cloud, DDD-style modules, mono/micro runtime, idempotency, outbox, and dead-letter flows.
  • Documentation governance: architecture rules, requirements, database design, runbooks, readiness checks, TODO lifecycle, and commit memory.
  • Language tooling: ANTLR grammars, LSP servers, diagnostics, formatting, semantic tokens, references, and editor previews.
  • AI productization: model inference, OpenAI-compatible workflows, streaming completion UX, and rich editor extensions.

Stack & Design

System Design DDD Architecture Governance AI Agent Workflow LSP

Java Spring Python PyTorch TypeScript React VS Code IntelliJ IDEA

Featured Work

Project Area Notes
bacon AI Agent Engineering OS 0-to-1 backend architecture for AI-agent collaboration: context routing, executable architecture rules, task lifecycle, quality gates, and commit memory.
sandwich Legacy modernization Applying the same AI-agent-friendly governance model to an older Java/Spring system with scoped docs, architecture tests, TODO lifecycle, and incremental boundary cleanup.
Language tooling TypeScript / ANTLR / LSP / IntelliJ Grammar-driven IDE and VS Code tooling with diagnostics, formatting, semantic tokens, references, parser tests, and preview workflows.
wechat-tiptap React / Tiptap / AI Editor Rich-text editor with custom extensions, table/image tooling, AI magic node, and streaming completion interaction.
Qwen2.5-Sign Python / Transformers / Gradio Text-to-sign inference app with model loading, generation pipeline, label mapping, and lightweight WebUI.

GitHub Snapshot

thundax's GitHub profile details

thundax's GitHub stats thundax's most committed languages thundax's productive time

Pinned Loading

  1. openspg-schema-highlighter-idea-plugin openspg-schema-highlighter-idea-plugin Public

    An IDEA plugin for OpenSPG schema syntax highlighting

    Java 8 1

  2. vscode-extension-openspg-schema vscode-extension-openspg-schema Public

    TypeScript 8

  3. alin995/wechat-tiptap alin995/wechat-tiptap Public

    A WeChat-style WYSIWYG editor,with AI powered and wonderful table extension and image extension

    TypeScript 52 4

  4. Qwen2.5-Sign Qwen2.5-Sign Public

    Text-to-Chinese-Sign model base on Qwen2.5

    Python 6 1

  5. bacon bacon Public

    Agent-first Java 后端工程范式:以文档路由、DDD 分层、多域协同、单体/微服务双形态、架构测试与质量门禁,支撑 AI Agent 稳定参与复杂工程交付。

    Java 9

  6. sandwich sandwich Public

    简洁外观之下的分层秩序。

    Java 3