I find OpenClaw and (more so) Hermes Agent useful for software development, research, and writing - but I refuse to run them anywhere that is not deeply-sandboxed and has no access to most of my digital life data.

OK, everyone makes their own decisions re: privacy and security. Personally, I am comfortable running OpenClaw and Hermes Agent on a rented VPS (preferably in a docker container on a VPS) and allow limited access to (some of) my GitHub repos. Both tools are useful, even in such a limited mode of operation. I just don't see value vs. risk allowing access to email, messaging apps, access to my personal computer, etc.

It is close to zero overhead to SSH/Mosh to a VPS, get inside a container to work. Why risk infecting your personal or corporate computer?