Posts by Tag

Development

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

macOS

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

Back to top ↑

iOS

Back to top ↑

Language

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

PC

Back to top ↑

Apple

Back to top ↑

Ruby

Back to top ↑

Claude Code

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

[Claude Code] Building a Real-Time Agent Dashboard

23 minute read

How I built a real-time monitoring dashboard to visualize what 19 Claude Code subagents are doing - from a failed Gather Town experiment to a practical WebSocket-powered control center.

Back to top ↑

Playground

Back to top ↑

Terminal

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

Back to top ↑

Automation

Back to top ↑

MCP

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

Objective-C

Back to top ↑

Software Engineering

Back to top ↑

CI/CD

Back to top ↑

Python

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

LLM

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

[LLM] Setting Up Ollama Remote Access

1 minute read

Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.

Back to top ↑

Swift

Back to top ↑

SmartHome

Back to top ↑

CS

Back to top ↑

fastlane

Back to top ↑

Agent

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

[Kiro] Agent Configuration

3 minute read

A guide covering agent creation, configuration, prompt modularization, and sub-agent usage in Kiro.

Back to top ↑

Shell

Back to top ↑

Blog

Back to top ↑

Jekyll

Back to top ↑

AI

Back to top ↑

Kiro

[Kiro] Agent Configuration

3 minute read

A guide covering agent creation, configuration, prompt modularization, and sub-agent usage in Kiro.

Back to top ↑

Agentic Coding

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

[Claude Code] Building a Real-Time Agent Dashboard

23 minute read

How I built a real-time monitoring dashboard to visualize what 19 Claude Code subagents are doing - from a failed Gather Town experiment to a practical WebSocket-powered control center.

Back to top ↑

Synology

Back to top ↑

NAS

Back to top ↑

IoT

Back to top ↑

SmartThings

Back to top ↑

SSH

Back to top ↑

Package Management

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

Homebrew

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

Back to top ↑

Git

Back to top ↑

Oh-My-Zsh

Back to top ↑

Zsh

Back to top ↑

Plugin

Back to top ↑

Xcode

Back to top ↑

Network

[LLM] Setting Up Ollama Remote Access

1 minute read

Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.

Back to top ↑

Minimal Mistakes

Back to top ↑

Column

Back to top ↑

Ollama

[LLM] Setting Up Ollama Remote Access

1 minute read

Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.

Back to top ↑

LangChain

Back to top ↑

Side Project

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

UIKit

Back to top ↑

Server

Back to top ↑

Java

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

Back to top ↑

Control Flow

Back to top ↑

ZigBee

Back to top ↑

Mathematics

Back to top ↑

Certificate

Back to top ↑

CocoaPods

Back to top ↑

SCM

Back to top ↑

GitHub

Back to top ↑

Key

Back to top ↑

Alfred

Back to top ↑

Command Line

Back to top ↑

Visual Studio Code

Back to top ↑

VSCode

Back to top ↑

RubyGems

Back to top ↑

CLI

Back to top ↑

Agentic Coding Assistant

Back to top ↑

SwiftUI

Back to top ↑

Swift Package Manager

Back to top ↑

Claude

Back to top ↑

DIY

Back to top ↑

Milvus

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

Windows 11

[LLM] Setting Up Ollama Remote Access

1 minute read

Configuring the OLLAMA_HOST environment variable and Windows Firewall to access a local LLM from other devices on the same network.

Back to top ↑

HyDE

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

RAG

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

MLX

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

Qwen

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

LangGraph

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

iOS 13

Back to top ↑

Learning Resource

Back to top ↑

Data Type

Back to top ↑

Operator

Back to top ↑

Spring

Back to top ↑

Maven

Back to top ↑

Gradle

Back to top ↑

Eclipse

Back to top ↑

Loop

Back to top ↑

Branch

Back to top ↑

PhotoStation

Back to top ↑

Nginx

Back to top ↑

Domain

Back to top ↑

OOP

Back to top ↑

Class

Back to top ↑

Method

Back to top ↑

Fundamental

Back to top ↑

Prime Number

Back to top ↑

Number Theory

Back to top ↑

SSL

Back to top ↑

Let's Encrypt

Back to top ↑

LFS

Back to top ↑

Theme

Back to top ↑

iOS 15

Back to top ↑

Xcode 12

Back to top ↑

Event

Back to top ↑

Keynote

Back to top ↑

iPad

Back to top ↑

iPad Mini

Back to top ↑

iPhone 13

Back to top ↑

Apple Watch Series 7

Back to top ↑

SSH Config

Back to top ↑

SSH Key

Back to top ↑

TimeZones

Back to top ↑

Workflow

Back to top ↑

Spaces

Back to top ↑

Mission Control

Back to top ↑

Python3

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

PIP

[Python] Installing PIP

less than 1 minute read

How to install PIP, the package manager for Python 3.

Back to top ↑

Finder

Back to top ↑

Path

Back to top ↑

Router

Back to top ↑

ASUS

Back to top ↑

RT-AX3000

Back to top ↑

HTTPS

Back to top ↑

Security

Back to top ↑

Action

Back to top ↑

Log

Back to top ↑

CSS

Back to top ↑

Responsive

Back to top ↑

Troubleshooting

Back to top ↑

rbenv

Back to top ↑

Version Management

Back to top ↑

Bundler

Back to top ↑

Bundle

Back to top ↑

JDK

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

Back to top ↑

OpenJDK

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

Back to top ↑

Temurin

[Java] Installing OpenJDK

less than 1 minute read

How to install Eclipse Temurin OpenJDK on macOS using Homebrew.

Back to top ↑

Claude Opus

Back to top ↑

VPN

Back to top ↑

L2TP

Back to top ↑

IPSec

Back to top ↑

Obsidian

Back to top ↑

Career

Back to top ↑

Modular Architecture

Back to top ↑

Private Spec Repo

Back to top ↑

Clean Swift

Back to top ↑

Dependency Injection

Back to top ↑

i18n

Back to top ↑

Multilingual

Back to top ↑

Trigonometry

Back to top ↑

UI

Back to top ↑

Code Review

Back to top ↑

GitHub Actions

Back to top ↑

STT

Back to top ↑

TTS

Back to top ↑

whisper.cpp

Back to top ↑

Google Cloud TTS

Back to top ↑

QuickTime Player

Back to top ↑

BlackHole

Back to top ↑

Audio MIDI Setup

Back to top ↑

dotfiles

Back to top ↑

Core ML

Back to top ↑

coremltools

Back to top ↑

Machine Learning

Back to top ↑

PyTorch

Back to top ↑

RS485

Back to top ↑

Home Assistant

Back to top ↑

Wallpad

Back to top ↑

LAN

Back to top ↑

Ethernet

Back to top ↑

Cable Management

Back to top ↑

Zigbee

Back to top ↑

Sonoff

Back to top ↑

Thin-Film Contact Sensor

Back to top ↑

iTerm2

Back to top ↑

AppleScript

Back to top ↑

Docker

Back to top ↑

Docker Compose

Back to top ↑

GHCR

Back to top ↑

GitHub Container Registry

Back to top ↑

Qwen3

Back to top ↑

NVIDIA

Back to top ↑

Magnific Popup

Back to top ↑

JavaScript

Back to top ↑

jQuery

Back to top ↑

Scapple

Back to top ↑

Node.js

Back to top ↑

TypeScript

Back to top ↑

Swagger UI

Back to top ↑

OpenAPI

Back to top ↑

Vercel

Back to top ↑

uv

Back to top ↑

PyCharm

Back to top ↑

LCEL

Back to top ↑

Prompt Engineering

Back to top ↑

Embeddings

Back to top ↑

Information Retrieval

Back to top ↑

AWS Bedrock

Back to top ↑

Subagent

Back to top ↑

Dashboard

[Claude Code] Building a Real-Time Agent Dashboard

23 minute read

How I built a real-time monitoring dashboard to visualize what 19 Claude Code subagents are doing - from a failed Gather Town experiment to a practical WebSocket-powered control center.

Back to top ↑

WebSocket

[Claude Code] Building a Real-Time Agent Dashboard

23 minute read

How I built a real-time monitoring dashboard to visualize what 19 Claude Code subagents are doing - from a failed Gather Town experiment to a practical WebSocket-powered control center.

Back to top ↑

Business

Back to top ↑

cmux

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

Back to top ↑

Ghostty

[cmux] A Ghostty-Powered Native macOS Terminal for Parallel AI Agents

4 minute read

cmux is a native Swift + AppKit macOS terminal that embeds the Ghostty engine and is built specifically for running multiple agentic coding assistants like Claude Code, Aider, and Cline side by side. This post covers installation, core features, and keyboard shortcuts.

Back to top ↑

Apple-Silicon

Back to top ↑

Tool-Calling

Back to top ↑

Quantization

Back to top ↑

Kafka

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

MongoDB

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

Spring Boot

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

FastAPI

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

SSE

[Agent] Yangsiljang, a Real Estate Law & Precedent RAG Chatbot Built as a Side Project

21 minute read

A breakdown of the architecture and implementation details behind Yangsiljang, a real estate law and precedent RAG chatbot built as a side project. The frontend was built with Claude Code’s help; the backend was written from scratch. Topics covered include a custom Korean tokenizer build for Milvus, Qwen3 embedding/reranker, HyDE, SSE streaming, and data ingestion from the Korean Legislative Service.

Back to top ↑

Mollo

Back to top ↑

Koog

Back to top ↑

Mastra

Back to top ↑

Pydantic AI

Back to top ↑

Apple Silicon

Back to top ↑

OpenAI

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

Anthropic

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

Korean Persona

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

Nemotron

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑

User Research

[Agent] korea-persona-interview, a Korean Synthetic Persona Interview Tool Powered by CLI and MCP

28 minute read

A writeup of korea-persona-interview, a side project that automates Korean synthetic persona interviews. It layers multi-turn interviews, automatic follow-ups, and persona drift detection on top of NVIDIA’s Nemotron-Personas-Korea dataset to validate business hypotheses quickly. The post also covers the design pattern that lets three entry points (CLI, MCP server, and MCP orchestrator) share a single core.

Back to top ↑