·16 min readAI
Building an MCP server with TypeScript
A step-by-step guide to building your own Model Context Protocol server in TypeScript to give AI assistants access to custom tools.
Blog
Thoughts on AI tooling, Linux, developer workflows, and whatever else I find interesting.
115 posts · 111,000+ words · ~9 hours of reading
····
Series
View allThe Self-Hosting Journey
From why to how. Setting up and running your own services at home.
8 parts
Docker Fundamentals
From first container to production-ready images.
4 parts
The Linux Switch
Making the move from Windows to a full Linux development workflow.
6 parts
Running AI Locally
Setting up and using large language models on your own hardware.
5 parts
Start here
·4 min readSelf-Hosting
The case for self-hosting
Why I self-host services instead of relying on SaaS, what I run, and an honest look at the tradeoffs involved.
·4 min readHomelab
What is a homelab and why would you want one?
An introduction to homelabs, what they are, why developers and tech enthusiasts build them, and how to get started without spending a fortune.
·4 min readAI
Comparing AI coding assistants: Claude Code, Cline, and OpenCode
An honest comparison of the AI coding tools I have used, what each does well, and which one fits different workflows.
·7 min readOutdoor Tech
Meshtastic: building an off-grid communication network
How Meshtastic turns cheap LoRa hardware into a mesh communication network that works without cell towers, Wi-Fi, or internet, and why it is perfect for outdoor adventures.
202629 posts
·15 min readHomelab
Uptime Kuma told me everything was fine. It wasn't.
Green checkmarks are not observability. Here is what I learned building a real monitoring stack.
·15 min readAI
What agentic coding actually looks like
Agentic coding changed how I build software. Not in the way the hype suggests.
·16 min readAI
Hermes Agent by Nous Research: the AI agent that actually cares about security
What Hermes Agent is, how it compares to OpenClaw on security and usability, and why it earned my trust.
·10 min readAI
How I would design an ad platform for LLMs
A technical breakdown of how a middleware ad layer for LLM APIs could work, why the economics demand it, and whether it should exist at all.
·11 min readWeb Dev
Why I built Omnibase: a universal database MCP server
I got tired of copy-pasting query results between DataGrip and AI agents. So I built an MCP server that gives AI agents secure, direct access to any database.
·7 min readWeb Dev
Delta libraries: how diffing works and which library to use
What delta libraries do, how diff algorithms work under the hood, and a practical comparison of the most popular options in the JavaScript ecosystem.
·6 min readWeb Dev
Offline-first apps: harder than it sounds
Building apps that work without internet is one of those things that seems straightforward until you actually try it. Here is what makes it hard and how to approach it.
·11 min readAI
Building RAG pipelines with local models
How to build a retrieval-augmented generation pipeline using local models and your own documents, without sending data to cloud APIs.
·3 min readAI
Using OpenRouter to access multiple AI models
How OpenRouter gives you a single API to access models from OpenAI, Anthropic, Google, and others without managing multiple accounts.
·5 min readOutdoor Tech
Starlink Mini: internet anywhere and peace of mind in remote places
How the Starlink Mini changed how I think about working remotely and adventuring in places with no cell coverage.
·3 min readAI
How agent skills work
What agent skills are, how they extend AI coding assistants with reusable workflows, and why they matter for developer productivity.
·3 min readAI
AI-assisted code review workflows
How I use AI tools to review code before committing, catch bugs early, and maintain consistency across projects.
·12 min readAI
What is an MCP server and why should you care?
An introduction to the Model Context Protocol, what MCP servers are, and how they let AI assistants interact with external tools and data.
·7 min readOutdoor Tech
Meshtastic: building an off-grid communication network
How Meshtastic turns cheap LoRa hardware into a mesh communication network that works without cell towers, Wi-Fi, or internet, and why it is perfect for outdoor adventures.
·11 min readAI
Getting structured output from language models
Techniques for getting LLMs to return JSON, typed objects, and other structured formats reliably, from prompt engineering to constrained decoding.
·2 min readAI
OpenCode: an open-source AI coding assistant
A look at OpenCode, an open-source terminal-based AI coding tool, and how it fits into my development workflow.
·9 min readAI
Fine-tuning small language models for specific tasks
A practical introduction to fine-tuning small LLMs for domain-specific tasks using tools like Unsloth and LoRA.
·4 min readOutdoor Tech
Kiwix: carrying Wikipedia (and more) offline
How Kiwix lets you download entire knowledge bases for offline access, and why I keep it on my devices for travel and remote adventures.
·3 min readSelf-Hosting
Self-hosting with Coolify: a PaaS on your own server
How Coolify turns your VPS into a Heroku-like platform for deploying apps, databases, and services with a clean web UI.
·4 min readAI
Comparing AI coding assistants: Claude Code, Cline, and OpenCode
An honest comparison of the AI coding tools I have used, what each does well, and which one fits different workflows.
·2 min readAI
Getting started with Open WebUI and Ollama
How to run local LLMs on your own machine with Ollama and put a clean web interface on top with Open WebUI.
·5 min readOutdoor Tech
What is LoRa and why does it matter for off-grid communication?
An introduction to LoRa radio technology, how it enables long-range communication without cellular or Wi-Fi, and why it is gaining traction with outdoor enthusiasts and tinkerers.
·3 min readLinux
Setting up a productive dev environment on Linux
The actual tools, terminal setup, and configuration I use for web development on Linux.
·16 min readAI
Building an MCP server with TypeScript
A step-by-step guide to building your own Model Context Protocol server in TypeScript to give AI assistants access to custom tools.
·3 min readLinux
Why I use Linux for web development
My case for using Linux as a web development environment, and the practical advantages it has over Windows.
·4 min readDeveloper Tools
Why shadcn/ui changed how I build React interfaces
What makes shadcn/ui different from traditional component libraries, and why copying components into your project is actually the better approach.
·3 min readDevOps
Automating workflows with n8n
How I use n8n as a self-hosted alternative to Zapier for connecting services and automating repetitive tasks.
·16 min readAI
What HuggingFace actually is
I thought HuggingFace was just GitHub for AI models, but that comparison sells it way short.
·3 min readWeb Dev
Deploying apps with Railway
How Railway makes deploying web applications simple without giving up control, and why I use it for side projects.
202527 posts
·12 min readAI
Running local LLMs on a consumer GPU
What you need to run large language models locally, which models fit on consumer hardware, and how to get the best performance.
·6 min readWeb Dev
Why I moved from Vercel to Cloudflare Pages
Vercel is great, but Cloudflare Pages with OpenNext gives me more control, better pricing, and no vendor lock-in for my Next.js apps.
·3 min readLinux
Why Pop!_OS is my Linux distro of choice
What makes Pop!_OS stand out as a Linux distribution for developers, and why I chose it over Ubuntu, Fedora, and Arch.
·4 min readHomelab
TrueNAS: reliable storage for your homelab
Why I use TrueNAS for network storage in my homelab, how to set it up, and the features that make it worth running over a simple file share.
·5 min readHomelab
Proxmox Backup Server: incremental backups done right
Why I use Proxmox Backup Server for my homelab backups, how incremental backups save massive amounts of storage, and how to set it up.
202422 posts
·5 min readWeb Dev
What nobody tells you about side projects
Most side projects die. Here is what I have learned about why, and the few things that actually help.
·3 min readNetworkingSelf-Hosting
AdGuard Home: DNS-level ad blocking for your network
How AdGuard Home compares to Pi-hole for network-wide ad blocking, and why I switched to it for my homelab.
·4 min readWeb Dev
Understanding WebSockets for real-time features
How WebSockets work, when to use them over regular HTTP, and a practical example of adding real-time updates to a web app.
·8 min readWeb Dev
Making maps work offline with PMTiles
How the PMTiles format enables offline-capable maps by serving vector tiles from a single static file, and how I use it in Landbound.
·3 min readDeveloper Tools
Git workflows that actually work for solo developers
Practical git strategies for when you are the only developer on a project, without the overhead of team-oriented workflows.
202322 posts
·12 min readSelf-Hosting
Year in review: what I self-hosted in 2023
A look back at every service I ran on my own hardware in 2023, what stuck, what I dropped, and what surprised me.
·3 min readDeveloper Tools
Why I switched from npm to pnpm
The practical reasons pnpm replaced npm as my default package manager, and why the switch was easier than expected.
·3 min readWeb Dev
REST vs GraphQL in practice
When GraphQL is worth the complexity and when REST is the better choice, based on using both in real projects.
·3 min readHomelab
My first homelab build: mistakes and lessons
What I got right and wrong when building my first homelab, and what I would do differently starting over.
·20 min readDevOps
How Docker image layers actually work under the hood
A deep dive into Docker image layers, union filesystems, content-addressable storage, copy-on-write, and why understanding this stuff makes you better at writing Dockerfiles.
202215 posts
·7 min readDatabases
How database indexes actually work
B-trees, query plans, and why adding an index does not always make things faster.
·4 min readWeb Dev
Why TypeScript is worth the setup cost
The practical benefits of TypeScript over plain JavaScript, and why the initial learning curve pays for itself quickly.
·3 min readNetworking
What is a reverse proxy and why do you need one?
A practical explanation of reverse proxies, why they matter for self-hosting, and how they route traffic to your services.
·5 min readWeb Dev
Understanding CORS (and why your API calls fail)
What CORS actually is, why browsers enforce it, and how to fix the errors without just slapping a wildcard on everything.
·6 min readDevOps
Why I use Cloudflare for everything
DNS, CDN, Pages, Workers, and a free tier that is hard to beat. Here is why Cloudflare has become my default for almost everything web-related.