Ho Chi Minh City, Vietnam / AI engineer and systems builder

I build AI-native systems that feel calm under pressure.

Hong Phuc builds developer tools, automation systems, and product-grade workflows for the new AI engineering stack. The work is technical, local-first, and designed to keep quality visible.

Mode

Local-first AI

Focus

Agents, DX, infra

Signal

Ship quality

~/lab/personal-os

$ codex run ship-agent-workflow --verify

lint: clean tests: 142 passed build: 31s

$ rtk gain --history --scope personal-os

signal extracted: 18 decisions, 4 risks, 3 follow-ups

featured projects

A garage shelf for systems that have scars, telemetry, and taste.

Project cards are built around engineering depth: constraints, runtime surfaces, quality loops, and the practical signal behind the artifact.

live.preview

active lab

Agentic Workflow Kit

A local-first toolkit for composing coding agents, command compression, durable memory, and verification loops into one calm engineering cockpit.

AgentsLLMsDeveloper Tools

1.8k

stars

42k

runs

180ms

latency

Codex workflows / RTK command compression / memory refreshinspect
live.preview

shipping

GitHub Digest

A daily technical intelligence feed that watches OSS motion, summarizes project deltas, and turns noisy GitHub activity into useful engineering context.

OSSAutomationSignals

120

repos

daily

briefs

-76%

noise

trend mining / RSS-ready / agent summariesinspect
live.preview

hardened

VideoMakerBot Stack

Containerized creative automation with separate CLI and GUI surfaces, persistent outputs, and reproducible runtime state for fast experimentation.

DockerMediaAutomation

2

services

shared

image

bind-mounted

state

Docker Compose / GUI binding / runtime persistenceinspect
live.preview

maintained

Virtual Cafe

A tiny, fast Vite experience cleaned up for real-world maintenance: dependency hygiene, stable Playwright checks, and careful UI behavior.

FrontendTestingPerformance

clean

audit

e2e

checks

lean

bundle

Playwright stabilization / selector waits / audit fixesinspect
about

Engineering philosophy for the AI-assisted era.

The center of gravity is still craft: simple boundaries, explicit tradeoffs, fast feedback, and tools that make good behavior easier.

01

Systems over spectacle

I like interfaces that make hard work feel understandable: sharp boundaries, useful defaults, observable behavior, and escape hatches when the abstraction leaks.

02

AI as a workshop, not a vending machine

The best AI workflows keep the engineer in the loop. Agents should compress toil, preserve intent, and leave a trail that future-you can trust.

03

Taste is an engineering constraint

Developer experience is not polish at the end. It is architecture, naming, ergonomics, feedback loops, and the discipline to delete what does not earn its place.

writing

Notes from the bench: architecture, AI workflows, and developer tooling.

Markdown-backed essays ship with static metadata, RSS output, and focused reading pages.

toolbox

The stack is boring where it should be, experimental where it pays rent.

Terminal setup, AI workflows, local LLM experiments, and quality gates are treated as one system.

Daily drivers

NeovimGhosttyzshpnpmDockerPlaywright

AI stack

CodexClaude Codelocal LLMsRAG notesagentsevals

Engineering loops

TDDtypechecklintruntime smoke testsdocs as memory

Product taste

LinearRaycastVercelshadcn/uiMotionminimal OS UIs
contact

Building an AI workflow, devtool, or serious technical system?

I like projects with hard constraints, clear taste, and enough technical depth to reward careful engineering.