I don't use OpenClaw I tried but found it fragile and it's personality off putting. I then tried NanoClaw, but found the lack of communication channels limiting and could never really get it to create skills that felt solid. I recently just switched to Hermes Agent (like last week) and it's the first one where it didn't feel like I was constantly needing to fix it, so at the moment I'm happy with it.

What do I use it for? I basically just use it as a personal assistant and a way to centralize a lot of other automations that I have elsewhere.

- I have an automation that rolls everything on my todo list over to the next day at 11:59pm

- I have one that checks the weather and tells me if it's going to be windy in the next few days since I need to bring the lawn furniture in

- I have it set up so that I can forward it email with invoices and it will extract the data from a PDF and enter it into a cost tracking sheet

- I have it check my outlook calendar and tell me if there are any 1:1 meetings where the other person has declined the invite (since Outlook doesn't show that clearly and I'd often show up to meetings and sit for 5 minutes before realizing the other person cancelled)

Nothing I'm doing is life changing, it all could be done using other tools, and honestly, for anything important, I want something more deterministic anyway, but I kind of love. It's just a low lift way to automate away minor annoyances through a single interface that I can access from just about anywhere. It's far from perfect, but I don't use it for anything where I need to to be perfect, so I'm happy.

The personality part, wow I thought I was the only one since no one else seems to have mentioned it anywhere. I agree.

During initial setup it even asked how you want its personality to be, I said upbeat and cheery. I know, I know, cliche for AI chatbots, but I kinda like it that way. But after that setup, it was nothing like it. Everything it says is just matter-of-fact-ly/stoic. That wouldn't be so bad if it didn't also have this quirk where if you point out its mistakes, it keeps saying it'll fix it, but it still does not work right the next time. It just keeps reassuring you it'll be fine, in that stoic way, and then it's not fine. That's enough to drive me nuts.

I got used to it now though and I don't get mad at it or scold it. I just learned to work with its quirks and still get tasks accomplished.