Working portfolio
Case Studies
How I built X, end to end: the problem, the debugging story, the fix and the measured result. This is my working portfolio.
- 20 end-to-end write-ups
- 4 flagship cases pinned first
- 3 production hosts · 162 containers
- EN + 中文
20 posts in this category
-
Running Production Infrastructure Solo: 162 Containers Across Three Hosts
One operator, three hosts, 162 containers in 78 compose stacks — Traefik, SSO, monitoring, mail, CI/CD and backups — and the two failures that changed how I verify my own numbers.
3 Hosts · 162 Containers -
How I Replaced Cloud TTS with a Self-Hosted Neural Voice Stack on an RTX 3060
How I migrated our production automation workflows from cloud speech APIs to a self-hosted CosyVoice 2 pipeline on a 12GB RTX 3060, integrated with Synology N8N.
RTX 3060 · 3.2 GB VRAM -
Loop Engineering Without a Coding Agent: The 11 Cron Jobs That Run My Infrastructure
Loop engineering is 2026's term for designing the system that prompts and checks an agent. I applied it to self-hosted infrastructure, not a codebase: 11 cron jobs, 8 with no AI at all.
11 Cron Jobs · 8 Loops -
Self-Healing Access Control for Digital Goods: NocoDB, n8n, and AList
How I built a five-workflow entitlement system that grants, expires, and continuously repairs customer file access — with a build-time code-sharing trick and a public endpoint designed to leak nothing.
NocoDB + n8n + AList -
From Audio to a 4-Minute Music Video: Orchestrating Gemini, AI Diffusion, and Filmora Editing
A complete production breakdown of building a 4-minute 1080p anime OP music video (Crescent Bay): AI music generation, Gemini storyboard prompting, iterative image-to-video rerolls, and Filmora VFX editing.
4-minute MV · one pipeline -
Your Own Speech-to-Text Server: Faster Than Typing, Private by Default
I run a self-hosted speech-to-text API on a single GPU PC. Dictation works from Windows, iPhone, iPad and Android — private, unlimited, and over 3x faster than typing.
3× faster than typing -
Shipping an AI Photo Editor as a WordPress Plugin: 22 Versions of Hard Lessons
From a single HTML file to a shipped WordPress plugin: the fal.ai async queue, a watermark that must never silently fail, optional lead capture, and five bugs that only appeared in production.
22 releases -
How I Self-Hosted a Mem0 Memory Stack (So My AI Agent Remembers)
A private, self-hosted memory layer for AI agents — mem0 API + LiteLLM + PostgreSQL with pgvector on a Synology NAS. Semantic memory under your control, not a third party's.
mem0 · pgvector · LiteLLM -
How I Built an AI Furniture Compositing Demo With FLUX.1 Kontext
Compositing furniture photos into styled room scenes with fal.ai FLUX.1 Kontext — the multi-image endpoint, the tainted-canvas fix, and why prompt enhancement had to go.
FLUX.1 Kontext -
How I Made My Own Songs with Suno AI
I wrote the lyrics, tuned the prompts, and shipped seven songs with Suno AI — folk ballads, a kids' tune, an anime-style Heart Sutra. Full workflow + the tracks.
-
How I Built the DigiKedai Telegram AI Bot
A customer-support AI bot that answers questions and provisions free-trial accounts over Telegram and WhatsApp — TypeScript, grammY, a Cloudflare tunnel webhook, and a self-hosted LiteLLM gateway.
24/7 instant reply -
How I Host This Blog: Astro, Gitea Actions, and Self-Hosted CI/CD
A walkthrough of the end-to-end pipeline that builds and serves this site — git-as-CMS, a self-hosted runner on my unRaid server, and Cloudflare in front.
Astro · Gitea Actions -
The Single-Writer Rule: Orchestrating Coding Agents Without Multi-Agent Chaos
Why letting multiple AI agents write code causes race conditions and drift, and how a single-writer architecture with isolated reviewers fixes it.
-
One Prometheus for unRaid, a Synology NAS, and a VPS: What I Got Wrong
Three hosts, one Prometheus, one Grafana. The coverage matrix, the storage total that counted one NAS volume three times, and the VM that exports no CPU frequency at all.
3 Hosts · 1 Prometheus -
When to Give Your Agent Physical Clicks (And When to Never Touch Them)
A 4-tier automation matrix for AI agents: comparing deterministic APIs, shell execution, background accessibility, and physical desktop simulation.
-
Syncing a Self-Improving AI Agent Across Machines
How I sync my Hermes agent's skills, config, and cron jobs between two PCs with a git-backed profile distribution — and why I sync manually instead of on a cron.
-
Why Your Headless Browser Can't Scrape Everything
Two second-hand marketplaces, two very different walls: Goofish blocks a headless browser with 'illegal access' while Carousell keeps serving data. The lesson is to read how a page delivers data before you reach for Playwright.
-
How I Vetted 20 VPS Providers in Three Hours with Parallel Subagents
A case study in orchestrating parallel AI subagents to run due diligence on 20 hosting providers — WHOIS, AUP, and reputation checks — collapsing a multi-hour research task into a structured, verifiable vendor scorecard.
20 VPS · 3 hours -
How I Built an Automated Music Video Pipeline with Remotion and Dockerized YouTube CDP
Explore an automated music video workflow using Remotion, Whisper, Docker and Chrome DevTools Protocol, from lyric alignment and rendering to YouTube publishing and multilingual subtitles.
Remotion · Docker CDP -
Why I Built a Video Knowledge Base: Turning Saved Short Videos into Searchable Notes
Why saving short videos to bookmarks is a dead end, and how I built a local ASR and AI pipeline to convert them into searchable notes with Click-to-Seek video sync.
