I usually connect with my server via ssh in a terminal and run basic commands. What's a better, more efficient and modern way of doing that? Especially considering ai and documentation along the way? I wonder if there's a better approach than "connect from remote and act local". Is there a method to "code local and push to remote"?

I use a fedora server with podman, caddyfile and vi.

you are viewing a single comment's thread
view the rest of the comments
[–] 11 points 1 day ago* (last edited 1 day ago) (2 children)

I created git repos on my main workstation for each homelab server/service I maintain that keeps:

  • documentation
  • notes
  • lessons learned
  • scripts, configs
  • runbooks
  • backup details
  • security audit details
  • log items that need attention
  • infrastructure

I just point a local LLM (offline model that runs on my workststion) into those repos and ask it to perform certain things on those servers. It can do things like update packages, install packages, make config changes, set/check permissions, read logs (and fix errors in real time), and check the health of the overall system.

I have it run pre backups before making changes, then post backups once its done.

Once changes are in place and everything is running okay, I ask it to update documentation in the repo and tag the release.

I use opencode that connects to a llama.cpp service. opencode lets me gate the AI so that any elevated commands that it needs to run (e.g. sudo or ssh), I have to approve it. It cant just go around making changes without permission.

  • source
  • hideshow 2 child comments
  • [–] 2 points 20 hours ago (1 child)

    What models are you using? What hardware are you running them on? I’m curious if I can replicate your success

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 19 hours ago*

    Hardware I'm running:

    • 8/16 AMD CPU
    • 32GB system RAM
    • 12GB GPU VRAM (AMD)

    I'm mainly using these MoE models:

    Qwen-3.6-35B-A3B

    • Q4_K_M quant quality
    • 128k context (conversation length before it compacts)
    • Gives me about 260 prefill and 19 token gen speeds

    Gemma4-26B-A4B

    • Q8 quant quality
    • 128k context length
    • Gives me about 190 prefill and 14 token gen speeds
  • source
  • parent