I think I’m close to my “this is the way” moment with local AI and agents. I’ve been learning a lot in my free time, but I’m not a developer by any means. Here’s where I’ve landed:
Two machines. An always-on server (Ubuntu or Proxmox) an old gaming PC is great for this, and a portable daily driver for learning and building. Rent it or build it, whatever works financially.
The stack. Docker, n8n for automation, GPUStack/vLLM for running models locally, Backrest for backups. The basics for automation and inference.
The skills. Python basics, APIs, general coding. This is by far the longest part.
The idea. Automate what you can, use inference where you can’t. Scripts handle the clicking, moving and organising. Agents step in when something needs thinking, writing, debugging, judgement calls.
Find a problem, solve it in a way a person would actually enjoy using, repeat.
[link] [comments]