<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Linux on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/linux/</link><description>Recent content in Linux on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 24 Mar 2026 07:30:00 +0100</lastBuildDate><atom:link href="https://renezander.com/tags/linux/index.xml" rel="self" type="application/rss+xml"/><item><title>Linux VPS AI Development Setup: Debian, Claude Code, MCP</title><link>https://renezander.com/blog/linux-vps-ai-development-setup/</link><pubDate>Tue, 24 Mar 2026 07:30:00 +0100</pubDate><guid>https://renezander.com/blog/linux-vps-ai-development-setup/</guid><description>&lt;p>My laptop sleeps. My agents do not. That is the whole reason I run a Linux VPS AI development setup instead of coding AI agents against a local Python venv and calling it a day.&lt;/p>
&lt;p>Everything I ship, the TickTick MCP server, the Telegram bot that long-polls Claude Opus, the cron driven morning briefings, the customer profiling pipeline, runs on one Debian box. No Kubernetes. No Docker Swarm. Just systemd, bash, and the Anthropic SDK. This tutorial is the exact sequence I use when I provision a new VPS for an AI project, from a fresh Hetzner image to a working Claude Code CLI with MCP clients wired up.&lt;/p></description></item><item><title>Systemd Services for AI Servers: Production Setup on Linux</title><link>https://renezander.com/blog/systemd-services-ai-servers/</link><pubDate>Sat, 21 Mar 2026 07:00:00 +0100</pubDate><guid>https://renezander.com/blog/systemd-services-ai-servers/</guid><description>&lt;p>I run a TickTick MCP server, a Telegram bot that routes through Claude Opus, and ten scheduled AI agents on a single Debian VPS. None of them run in Docker. All of them run as systemd services or systemd timers.&lt;/p>
&lt;p>This is the setup guide for running systemd services for AI servers the way I actually do it in production. Unit files, logs, timers, resource limits, and the security hardening that matters. No container orchestration, no Kubernetes, no Docker Compose YAML. Just systemd, because for single-host AI workloads it is the right tool.&lt;/p></description></item></channel></rss>