I've been working on a home Hermes setup that I'm using to do a variety of things. So far, here's what I've done:

- Set up an in-house alternative to my Ring subscription for the cameras around my house. So far I have it real-time monitoring, complete with AI face recognition and interpretation of events, all on an internal web page. It also sends me alerts via Telegram.

- Set up a blog that I'm using to catalog these experiences with Hermes and AI in general

- Started working with multiple agents to do things when appropriate. My main model right now is glm-5.2 for cloud, and Qwen3.6b-IQ4 (4-bit quantized) running locally. It only takes 18GB of VRAM on my 4090, so I have plenty of overhead. I'm also using Hindsight instead of the MEMORY.md that Hermes natively uses.

- Setup local image generation, with the local Qwen model, using ComfyUI w/Flux.

- All of the above isn't including the numerous smaller jobs (like setting up Telegram, setting up automated cloud backups, troubleshooting Linux issues, etc) that I've been using Hermes for.

Future plans: I'm working on making a game with Godot, learning as I go. I haven't had Hermes do anything for that, and I don't want to really, except I may use local image gen for testing purposes, as I plan to engage an artist for any graphical work in the final product.

I'm doing all of this just a learning experience. It's been really fun so far.