Most “agent frameworks” are libraries that push the hard parts of production—orchestration, secrets, versioning, and audit logging—into ad-hoc glue code. As teams move from “chatting with a PDF” to shipping internal copilots, the need for a governed, observable runtime becomes undeniable. This is where Dify enters the stack. It’s a self-hostable “LLM app runtime” designed to turn agentic prototypes into real business services. What is Dify used for in LLM application development? Dify is an open-source LLM application development platform that provides a unified workflow engine, model gateway, and RAG subsystem. It allows developers to model AI applications as explicit directed acyclic graphs (DAGs), enabling governed orchestration of LLM calls, external tools, and retrieval policies with built-in operational telemetry and multi-tenant isolation. ...

The Goal I have a DigitalOcean Kubernetes cluster running services like n8n (workflow automation), SearXNG (search), PostgreSQL, and Redis. I also have a Raspberry Pi 5 running OpenWrt as my home router. I wanted every device on my WiFi – laptops, phones, tablets – to be able to access my K8s services directly by ClusterIP, without installing Tailscale (or any VPN client) on each device. The result: my wife can open http://10.245.15.122:5678 on her laptop and hit n8n. My iPad can reach SearXNG. Any device on the WiFi just… works. The OpenWrt router handles the encrypted tunnel transparently. ...

Series: How I Used Claude Code to Slash My Cloud Bill by 63% Part 1: The $198/Month Wake-Up Call Part 2: Migrating 7 Static Sites to Cloudflare Pages Part 3: Killing the Load Balancer with Cloudflare Tunnel Part 4: Building a Home Router with a Raspberry Pi 5 Part 5: Connecting Everything with Tailscale Part 6: The Final Architecture - $74/mo and Zero Regrets (you are here) The Before Architecture Here’s what I was running before this project started: ...

Series: How I Used Claude Code to Slash My Cloud Bill by 63% Part 1: The $198/Month Wake-Up Call Part 2: Migrating 7 Static Sites to Cloudflare Pages Part 3: Killing the Load Balancer with Cloudflare Tunnel Part 4: Building a Home Router with a Raspberry Pi 5 Part 5: Connecting Everything with Tailscale (you are here) Part 6: The Final Architecture - $74/mo and Zero Regrets The Problem: Private Access Without Public Exposure After the Cloudflare Tunnel work in Part 3, I had one service (n8n) accessible through a tunnel and everything else locked down inside the Kubernetes cluster. But I had other internal services I wanted to reach from my home network – things like SearXNG, Redis Commander, and the Kubernetes dashboard. None of these should be publicly accessible. I don’t want a public endpoint for my search engine or my database admin tool. ...

Series: How I Used Claude Code to Slash My Cloud Bill by 63% Part 1: The $198/Month Wake-Up Call Part 2: Migrating 7 Static Sites to Cloudflare Pages Part 3: Killing the Load Balancer with Cloudflare Tunnel Part 4: Building a Home Router with a Raspberry Pi 5 (you are here) Part 5: Connecting Everything with Tailscale Part 6: The Final Architecture - $74/mo and Zero Regrets The Pi on the Desk I had a Raspberry Pi 5 (8GB) sitting on my desk running Debian trixie. It was serving as an occasional dev box, but mostly collecting dust. Meanwhile, I was paying Comcast for a gateway that doubled as a mediocre WiFi router. The gateway WiFi was fine for my wife’s devices, but I started thinking: what if I ran my own router? ...