I’ve been running a home lab since 2002, but the last few weeks it’s turned into something closer to a full enterprise analog: NetBox as the source of truth, Ansible with vault-encrypted credentials, Semaphore running playbooks from Git, automated encrypted config backups, and a Telegraf/InfluxDB/Grafana monitoring stack. Self-hosted GitLab with a GitHub mirror for version control.
The newest piece: a fully local AI coding agent. No cloud, no API costs, nothing leaving my network.
Running this on consumer hardware taught me a few things. Unsupported AMD GPUs won’t do ROCm (though some recent community patches are changing this), so Vulkan ended up being the fallback that simply works. The bigger problem is by default agentic coding tools send their full tool schema with every request, and on a small local model that overhead is brutal, roughly a 10k token prompt before your question even gets read. The fix was scoped agents: read-only agents for codebase questions, write-enabled agents only where needed. Cutting the tool surface cut the overhead dramatically.
End result: I can ask an agent questions about my Ansible repos or have it draft playbooks matching my existing conventions, entirely offline. It’s slower than cloud models and I wouldn’t trust it unsupervised near anything production, but that was kind of the point. I wanted to understand the limitations behind “AI coding agent” before trusting one near real infrastructure.