Jairix — A fully self-hosted AI agent that planned my road trip through Spain

How I built a fully self-hosted AI agent on a consumer laptop — and used it to plan a 45-day camper trip through Luxembourg, France, and Spain, without sending a single byte to an external cloud service.

From Garage to RustFS: When Good Enough Isn't Enough Anymore

I migrated from MinIO to Garage this week. Now I'm migrating again — this time to RustFS. Here's why, and how I built a proper Helm chart to run it on my Talos cluster.

My Homelab Setup: Network, Bare Metal Kubernetes, and a Ridiculous Desktop

A deep dive into my home setup: a fully wired Gigabit network, a 5-node Talos Linux Kubernetes cluster, dual Synology NAS units, and a desktop build that has absolutely no chill.

Migrating from MinIO to Garage: So Long, and Thanks for All the Fish

MinIO killed its community edition. Here's how I migrated to Garage on my Talos/K8s homelab cluster.

Living With an AI Agent: Daily Workflows, Skills Integration, and What Actually Works

What does it actually look like to work with a personal AI agent day-to-day? Real workflows combining MCP servers, OpenClaw skills, and 4 weeks of production usage patterns. The good, the unexpected, and the genuinely useful.

Skills vs MCP Servers and the Future of Personal AI Agents

After building both OpenClaw skills and MCP servers, what did I learn about the right abstraction layer? And where are personal AI agents heading in the next 5 years? A reflection on tooling, standards, and the shift from AI-as-service to AI-as-infrastructure.

Agent Identity and Security: Building Safe AI With Real Agency

How do you build an AI agent with genuine agency that remains safe? Defense-in-depth with network isolation, identity-driven boundaries, permission documentation, and audit trails. Production lessons from 4 weeks of real usage.

Building Production MCP Servers: Auto-Generation and Granular Tools

How to build Model Context Protocol servers that actually work in production. Deep-dive in auto-generation from API routes, permission models, and why 13 small tools beat one smart tool.

From Cloud-Native Kubernetes to Bare Metal AI: The OpenClaw Journey

Why I moved my AI agent stack from Kubernetes to a bare metal laptop, what broke along the way, and the 98% success rate that followed. A technical journey through OpenClaw, Ollama, and production AI infrastructure.

Building an OpenAI-Compatible Research Agent with Thinking Mode

Deep dive into creating a production-ready research agent with LangGraph, streaming support, and OpenWebUI integration featuring collapsed reasoning sections