In April I wrote about OpenClaw — my self-hosted AI agent on a Hostinger VPS, wired to Telegram, email, calendar, and GitHub. That post ended with a short "What's Next" list. Three months later, most of it shipped — and the setup feels less like a…

I co-founded HalloCasa — a global real estate broker directory with listings, profiles, subscriptions, and courses. Organic search should be a major channel for us. But when I sat down to build an SEO strategy, I did not want to spend a day clicking…

You built on Lovable — React app, Supabase auth, Postgres. It works. Then your first DACH customer or pilot asks: Where is prod hosted? Where do login and data live? That question shows up fast in Germany, Austria, and Switzerland B2B — especially HR…

Part 2: Self-hosted insights on Hetzner A German client needed production in the EU on Hetzner — clear control over where customer data and login live. The product is Arc Rider Universe: the SaaS behind universe.arc-rider.com — Mission: Interface, a…

Part 1: EU production on Hetzner After prod went live on Hetzner — React app, self-hosted Supabase login, Postgres on EU VMs; dev still on Netlify + managed Supabase — we added self-hosted observability on a dedicated prod VM. Metrics, logs, traces…

I've been running OpenClaw on a Hostinger VPS for about a month now, and it has fundamentally changed how I work. What started as "let me try this AI agent thing" turned into a powerful assistant that saves me hours every week by automating routine…

The Problem: Context Amnesia Across AI Agents I work with multiple AI agents every day — Cursor IDE, OpenAI Responses API, ChatGPT or OpenClaw. On top of that, I juggle dozens of repositories spanning CDK infrastructure, Rust libraries, Python…

Introduction Building AI agents that work in production requires more than wrapping an LLM API. You need tool execution, streaming responses, cost management, and integration with existing systems. After evaluating several frameworks for ai-secure…

Introduction Building production-ready AI agents requires more than just a prompt and an LLM. You need infrastructure for state management, tool execution, and secure deployment. I recently built https://ai-secure.dev, a SaaS for automated security…

Learnings Try to have complex flows solely solved by the agent. And then write deterministic code. speed. Introduction Building production-ready AI agents requires more than just a prompt and an LLM. You need infrastructure for state management, tool…