Ask HN: What are the most autonomous AI agents you know of?

Hi all, I'm an engineer and most of my work with AI keeps me fairly closely in the loop - reviewing output or giving permissions. However, it's very clear that with enough permissions / MCPs, the LLM could do its own thing ~indefinitely.

I'm curious if anyone knows of any extremely autonomous AI agents which run in perpetuity or close to that?

Thanks for any answers, thoughts or ideas!