How I Built a Server That Runs AI Agents 24/7 (Full Setup)
Running multiple AI coding agents in parallel sounds great until you hit the real problems: agents dying when your laptop closes, no way to reach them from across the world, and rogue processes fighting your daily driver for CPU and RAM. This video works through every one of those problems systematically, building up a practical, cost-effective server setup designed specifically to keep a fleet of agents running around the clock. The solution is simpler and cheaper than you might expect — a modest Linux PC running terminal-based agents inside a persistent multiplexer session, reachable from anywhere via SSH over Tailscale. Along the way, the video covers why cloud instances, Kubernetes, desktop apps, and IDEs all fall short for this use case, and what to reach for instead: tools like Devbox for environment isolation, vals for secrets management, and MCP servers for notifications and external integrations. The result is a setup where persistence, accessibility, resource dedication, and agent isolation are all handled cleanly, for a one-time hardware cost that pays for itself against cloud pricing within a few months. #AIAgents #CodingAutomation #DevOps Consider joining the channel: https://www.youtube.com/c/devopstoolkit/join ▬▬▬▬▬▬ 🔗 Additional Info 🔗 ▬▬▬▬▬▬ ➡ Transcript and commands: https://devopstoolkit.live/ai/how-i-built-a-server-that-runs-ai-agents-24-7-full-setup 🎬 Nix for Everyone: Unleash Devbox for Simplified Development: https://youtu.be/WiFLtcBvGMU ▬▬▬▬▬▬ 💰 Sponsorships 💰 ▬▬▬▬▬▬ If you are interested in sponsoring this channel, please visit https://devopstoolkit.live/sponsor for more information. Alternatively, feel free to contact me over Twitter or LinkedIn (see below). ▬▬▬▬▬▬ 👋 Contact me 👋 ▬▬▬▬▬▬ ➡ BlueSky: https://vfarcic.bsky.social ➡ LinkedIn: https://www.linkedin.com/in/viktorfarcic/ ▬▬▬▬▬▬ 🚀 Other Channels 🚀 ▬▬▬▬▬▬ 🎤 Podcast: https://www.devopsparadox.com/ 💬 Live streams: https://www.youtube.com/c/DevOpsParadox ▬▬▬▬▬▬ ⏱ Timecodes ⏱ ▬▬▬▬▬▬ 00:00 Running AI Agent Fleet Remotely 01:52 From Chat to AI Agent Swarms 04:13 Building an AI Agent Server