I don't understand people running OpenClaw. I just full shot a prompt to create a better clone. Its extremely custom to my work and flow. I use it as a personal agent, emails, slacks + as a hardcore coding agent. If it sees a problem in email it will create a ticket, assign it to an agent monitor progress, get a PR ready for me - then it harasses me until I review the PR. If I ignore the PR it will call my wife. It can also reason on what emails need critical attention etc.
There are lots of relational databases today; MySQL, Postgres, Oracle etc. But IBM's System R established the pattern in 1974, and later IBM products SQL/DS and DB2. And of course their competitor, Oracle. OpenClaw might not have been the absolute exact first, but it did establish the pattern and is the head of the family tree of modern agents, stretching back, oh, about 7 months now. Of course there will be better architectures. Functional AI Agents deployable at home didn't exist a year ago.
OpenClaw deserves a lot of credit for making these things more accessible and understandable to people. It really popularized the idea of async agents. But yeah, I also created a different solution that I prefer.