> When are we going to build a safe version of this?
I built something similar to Clawdbot for my own use, but with a narrower feature set and obviously more focus on security. I'm now evaluating Letta Bot [0], a Clawdbot fork by Letta with a seemingly much saner development philosophy, and will probably migrate my own agent over. For now I would describe this as "safer" rather than "safe," but something to keep an eye on.
I was already using Letta's main open source offering [1] for my agent's memory, and I can already highly recommend that.