Been looking at this over the weekend. It genuinely seems like it could have some really cool use cases. However I just don't trust an AI enough to run unprompted with root access to a machine 24/7, even if it's sandboxed. As soon as I willingly integrate data into it, the sandboxing doesn't really matter, especially when I ask it to decide for itself how to process that data (which seems to be what they want you to do with it? Ask it to define its own skills?)
Most of the cool stuff here, i.e. automatic news or calendar summaries or hue light controls or Discord bot integration or what not, you can also just "vibecode" in an afternoon using regular Claude code. If you actually review said code, you then have the peace of mind of knowing exactly what gets triggered when. I don't really feel comfortable enough to give that control away yet.
And I also feel like the people who _do_ feel comfortable giving this control away also strongly overlap with people who really don't have the understanding to make an informed decision on it...
Most of the cool stuff here, i.e. automatic news or calendar summaries or hue light controls or Discord bot integration or what not, you can also just "vibecode" in an afternoon using regular Claude code. If you actually review said code, you then have the peace of mind of knowing exactly what gets triggered when. I don't really feel comfortable enough to give that control away yet.
And I also feel like the people who _do_ feel comfortable giving this control away also strongly overlap with people who really don't have the understanding to make an informed decision on it...