Risk, imo. I am running it, and constantly identify use cases but they each carry some kind of risk I can’t get past. And so for now I am using individual purpose-built Claude Code harnesses, which has much more cognitive overhead and isn’t wired into discord, but I can really control access.

They are centered around managing information in/out, or “hey siri have groceries delivered“.

Yes, I use it that way too. Usually for things like code changes on my project when I'm away from home. Besides that, it does market research for me, but those were the only things I've been able to do so far. I can't find a use case that really stands out.

The issue is the amount of security and privacy risks you're undertaking by using it and its third-party developed skills. The more access you give, the more powerful and useful it gets.

There's a lot of useful use cases for OpenClaw but I wish I had the guts.

I agree, and I think we should create our own skins for OpenClaw. Otherwise, the use cases are very limited.

The guts problem is real. I had the same thing, wanted to let agents run unsupervised but couldn't stomach the risk.

What actually helped was flipping it around. Instead of trying to trust the agent, I used the agent to help build something that watches it. I've got an OpenClaw setup on a Raspberry Pi and it helped plan, test, build, install, run and monitor its own security proxy. Deterministic rules, no LLM in the enforcement path, just pattern matching on every outbound tool call.

So now the agent runs, the proxy catches anything sketchy before it leaves the box, and I've got a dashboard I can check from my phone. Still wouldn't call it "safe" but at least I can see what's happening and it can't quietly exfiltrate stuff without tripping a rule.

Turns out "help me build the thing that constrains you" is a use case agents are surprisingly good at.

There are a lot of useful cases for OpenClaw, just like there are use cases for letting my dog drive my car. Still don’t let my dog drive though.