Local Proxy 도입을 통한 Claude Code와 Kiro 모델 구독 비용 최적화
I Taught Claude Code to Speak Kiro
I Taught Claude Code to Speak Kiro
the hybrid inference architecture quietly cutting ai costs by 60%
5종 Protocol Adapter 기반의 Codex 전용 LLM Local Proxy 구현
How I stopped fighting AI API chaos with a simple proxy
Why I Abandoned Electron & SPAs to Build a 128MB Local-First Desktop AI Agent
How I Gave My AI Agent Persistent Memory Without Modifying Its Code
System Design - 17. Service Discovery & Service Mesh: How Thousands of Services Find Each Other
docfx-remote-include: inline remote markdown into DocFX, and govern the assembled page
I built a Windows tool that turns screenshots into one searchable PDF — here's what I learned
Give Your AI Agent Persistent Memory Without Touching Its Internals
Docker vs Kubernetes: Stop Comparing Them Like They Compete
That 0.8 second P99 Latency Cliff in Production Wasnt Supposed to Happen
Your AI Agent Doesn't Need an API Key: Entra Agent ID and Anthropic's Workload Identity Federation
Building ValoVault: The Per-Agent Skin Loadouts Riot Never Shipped
Deleting the 8.4GB Python Sidecar: Pure Go + CUDA with `CGO_ENABLED=0`
The Engineer Atlassian Laid Off Who Responded with a 38-Minute Documentary: What Every Leader Must Learn
El Ingeniero que Atlassian Despidió y Respondió con un Documental de 38 Minutos: Lo que Todo Líder Debe Aprender
The Daimon Java SDK: Chat, Stream, and Query Memory from 3 Lines of Java
A tmux sidecar for repeatable Claude/Codex workflows
Building a devcontainer for Topaz: workspace mounts, DNS wildcards, and why /etc/resolv.conf always wins