English | 中文

An open-source AI coding workflow and developer education lab for Chinese-speaking developers.

This repository documents practical AI-assisted development workflows, Agent experiments, tool evaluations, curated resources, reproducible notes, and real failure cases. It is not a news mirror and it is not a giant tutorial collection. The focus is on what was actually tried, what broke, what worked, and what can help developers build better workflows with AI.

Live Preview · AI Articles · AI Resources · Works & Open Source · Development Guidelines · Legacy Archive · Open Source Impact

• The official Codex guide: how to use /goal correctly

  A practical entry point for setting goals, validating progress, and keeping long-running AI coding tasks from drifting.

• Codex optimized my home network, and the result was absurdly good

  A real troubleshooting story that shows the boundary between AI diagnosis, command execution, and human review.

• Connecting Agent Workflow Kit to your project

  A useful starting point if you are thinking about adding Agent workflows to an existing project.

• I finally figured out Codex usage: output is not the most expensive part

  For readers who care about tokens, caching, cost, subscription limits, and practical usage accounting.

• Layweout: a WeChat article formatting workbench

  A small tool that grew from a real publishing workflow problem.

• How to get the most out of Codex

  A look at persistent threads, sidebars, automations, /goal, and how Codex can become a working system instead of only a coding assistant.

• AI Articles

  Real AI tool usage, model observations, industry notes, failure records, and practical workflow writeups.

• AI Resources

  GitHub projects, tools, and resources mentioned in the articles and worth bookmarking or trying.

• Works & Open Source

  Products, tools, content projects, and open-source work maintained or built by the author.

• Development Guidelines

  Notes on AI coding, project maintenance, collaboration, and Agent workflow practices.

• Legacy Archive

  The older bestJavaer materials covering Java, concurrency, JVM, operating systems, networking, MySQL, Spring, and interview topics.

• 2026-05-27 · OpenAI blocked my open-source sponsorship account
• 2026-05-25 · The official Codex guide: how to use /goal correctly
• 2026-05-24 · Codex optimized my home network, and the result was absurdly good
• 2026-05-21 · Connecting Agent Workflow Kit to your project
• 2026-05-19 · DeepSeek can leak other players' conversations
• 2026-05-19 · A detailed introduction to weread skills

• The content comes from real usage instead of rewritten product announcements.
• Failure paths and debugging notes are kept because, in the AI era, the troubleshooting process is often more valuable than the final answer.
• The resource pages are intentionally curated instead of trying to be exhaustive.
• The older bestJavaer materials remain available, while the active project direction moves toward AI tools, Agent workflows, and personal experiments.

bestJavaer used to be a Chinese learning repository for Java developers, covering Java, concurrency, JVM, operating systems, computer networks, MySQL, Spring, interview topics, and related developer education material.

That material is not removed. It has been preserved in archive-bestjavaer. The current main line is now cxuan-ai-labs: AI coding workflows, Agent experiments, open-source resources, and practical developer education for Chinese-speaking developers.

This repository uses a dual-license model:

• Documentation, articles, tutorials, images, and curated content are licensed under CC BY-SA 4.0.
• Code, scripts, tools, and software examples are licensed under MIT.

If a subdirectory or file declares a separate license, that local declaration takes precedence.