Quick terminology question… when you deploy one of these in OpenClaw, is the official term “agent”?

I’ve seen the project name, but I’ve never been quite sure what the canonical noun is for a running instance. Are they actually called “claws”, or is that just me over-literalizing the branding?

Very curious

The definition of "agent" with respect to AI has been hotly debated since at least the 1990s: https://simonwillison.net/2024/Oct/12/michael-wooldridge/

So there is no "correct" definition even to this day - and that vagueness makes the term difficult to have useful conversations around.

I've settled on "LLM making tool calls in a loop to achieve a goal", which I think is broad enough to cover what many people are talking about these days while being narrow enough to be useful.

On that basis Claude Code and OpenClaw are both examples of agents - they run tools and can loop until they've achieved the goal set for them by their user.

Agents usually refer to "coding agents" but they need a human in the loop.

What makes Claws Claws is that they run automatically without human intervention, BUT they're built around an Agent =)

It's like if you could tell Claude Code that "at 8am tomorrow morning check the weather at my current location and send me a Telegram message". It doesn't know how to wait until 8am, it'll just do it. Or it'll create some massive hack to do it.

A Claw is built for things like that and has a "memory" of stuff it needs to do in the future and the ability check it periodically.