I have a similar set up. I communicate/chat with the Hermes agent via Matrix chat client.

So rather than having to go to a bunch of different websites or apps to get things done, I've linked them all to Hermes (via skills) and chat with the Hermes agent on my phone.

I want a movie? I just say download XYZ. Shows up in Plex 5 min later.

I want to research something with multiple different perspectives? Rather than going to OpenWebUI and using that, I just asked a Hermes agent to examine an issue from multiple different viewpoints and get back to me with a conclusion.

It's the next paradigm in how people interact with computers.

100%. It's so natural, even to complete noobs that's it's hard to go back.

Except it's not. Even though us commandlinebros made fun of GUIs back when they came out, GUIs still have the property of being precise and unambiguous (to the machine, to the human requires design finesse and clear guidelines). There's no "Oopsie-boopsie! I made a little fucky-wucky and accidentally your entire production database, even though you told me not to do that!" with a CLI or GUI. With CLI and GUI, screwups of that sort are entirely PEBKACs. The fucky-wucky factor needs to be controlled in LLMs so that it's possible to communicate your exact intent to the machine and get the expected result every time. Of course if that's ever achieved we will have reinvented command processors "with extra steps".

Is a webapp with a frontend not a GUI? Thats what I meant.