# markhuang.ai I build AI systems, memory tools, and production software, then write down the decisions, mistakes, and tradeoffs that changed how I think. - Canonical: https://markhuang.ai - Language: en --- Hello, I'm Mark. AI architect writing about **systems that remember, fail, and improve**. I build AI systems, memory tools, and production software, then write down the decisions, mistakes, and tradeoffs that changed how I think. --- ## Featured Articles ### [Claude Max 20x Hit 100% on Day Four. Why I Moved to Codex](https://markhuang.ai/blog/why-i-cancelled-claude-max-for-codex) After Claude Max 20x hit its weekly limit on day four, I moved my coding work to Codex. Rising correction effort made the decision easier. My current setup uses Sol to plan, Luna to implement, Dense-Mem for context, and other model families for review. ### [I Keep Asking Why: The Mindset I Want to Keep in the AI Era](https://markhuang.ai/blog/i-keep-asking-why) A conversation with my wife made me examine how I became an engineer and architect: learning from people, asking why, testing assumptions, and owning decisions in the AI era. ### [I'm Aggressively Trying to Replace Myself With AI](https://markhuang.ai/blog/aggressively-trying-to-replace-myself-with-ai) AI becomes more useful as it learns more context, but every email, document, and story moves the privacy boundary. A personal reflection on automation, AI slop, focus, and builder responsibility. ### [What AI Benchmarks Measure: Scores, Context, and Usage Limits](https://markhuang.ai/blog/what-ai-benchmarks-actually-measure) A practical guide to AI benchmark scores, context windows, and usage limits—and why a higher score may not mean a better coding workflow. ### [AI MemMail: Let Dense-Mem Triage and Answer Your Business Inbox](https://markhuang.ai/blog/ai-memmail-dense-mem-email-agent) A practical setup guide for ai-memmail, the open-source Rust email agent that watches IMAP inboxes, recalls business context from Dense-Mem, and safely replies, forwards, or no-ops through SMTP. ### [Agentic Browser Automation Without Giving AI Your Login](https://markhuang.ai/blog/ai-browser-automation-without-sharing-login) A beginner-friendly tutorial for building scheduled or queue-driven agentic browser automation with Selenium, noVNC manual login, and a narrow API wrapper so agents can draft website forms without seeing credentials or controlling your PC. ### [I Might Be Wrong About Agentool](https://markhuang.ai/blog/i-might-be-wrong-about-agentool) A personal automation postmortem about building agentool to make AI CI workflows lighter, then realizing the real cost may be feature maintenance, orchestration complexity, and chasing SDK behavior that Claude Agent SDK and Codex SDK already own. ### [Stop Teaching Every AI From Scratch](https://markhuang.ai/blog/centralized-ai-knowledge-graph-dense-mem-case-study) A personal Dense-Mem reflection on the problems that pushed me beyond static skills and stale files toward dynamic shared memory, read-only automation context, import/export, and governed knowledge graphs. --- ## Featured Projects ### [Dense-Mem](https://github.com/markhuangai/dense-mem) Standalone HTTP MCP memory server for LLM hosts with durable graph memory, typed claims and facts, server-side embeddings, team/profile isolation, and recall. ### [golden-CLAUDE.md](https://github.com/Z-M-Huang/golden-CLAUDE.md) A masterpiece CLAUDE.md configuration to maximize Claude Code proficiency — curated rules, patterns, and guardrails for AI-assisted development. ### [AI MemMail](https://github.com/markhuangai/ai-memmail) Rust email agent that monitors IMAP inboxes, uses Dense-Mem knowledge over MCP plus safety rules to draft replies, forward, or no-op, and sends through SMTP with a React control panel. --- ## Published Work ### [Governed Enterprise AI Memory Beyond RAG: From Vector Retrieval to Permissioned Knowledge Graphs](https://doi.org/10.5281/zenodo.21403316) Explores how permissioned, provenance-preserving knowledge graphs can support enterprise AI memory beyond conventional vector retrieval. --- ## Explore current builds Dense-Mem is live as a free hosted demo for governed AI memory and team knowledge workflows. - [Try free demo](https://demo-dense-mem.markhuang.ai) - [Read docs](https://github.com/markhuangai/dense-mem/wiki) - [View repo](https://github.com/markhuangai/dense-mem) --- ## Certification - **Claude Certified Architect Foundations** — Foundations credential for applied AI architecture and implementation work. - **Claude Certified Architect - Professional** — Professional credential for designing and leading enterprise-scale Claude deployments, integrations, optimization, and governance.