How much do you automate anything in your life at all? Seems like most daily drudgery comes from physical tasks. Feed the dog. Take out the trash. Personally I can’t think of anything digital that could be automated that isn’t already. I wouldn’t be surprised if this the case for most people, with the exception of marketers and spammers which we are seeing a ton of adoption from with these tools.

I don't automate much because it's a pain.

I have a desktop at home.

When I'm at work, I often think of TODOs for home. I write them on a post it note, and then at home have to remember to add it to my TODO (no, I'm not going to manage TODOs on my phone - whole other conversation).

I'll soon set up my Claw to be able to add TODOs (just add, not modify/delete). Then at work, I'll simply record a voice message to it telling it my TODO.

Same goes for movies I want to watch, books I want to read, reminders, etc.

I'm particular about the weather information I want (often want cloud cover percentage and precipitation probability for a set of hours). I couldn't find a good app on my phone that gives me this information. It was always a trip to a web site, modify some options, and hit Submit. Now I just ask my Claw and he has a skill for precisely my needs.

Here's an analogy: I carry a Leatherman multitool wherever I go. People ask me why. They can't comprehend needing it often to make it worth the hassle. But now that I have it on me, I use the knife very often - several times a week. And I almost never reach for a screwdriver. But until you've had it on you for a while, you can't comprehend the utility.

Back in 2005, lots of people asked "Why would I want a camera on my phone?"

> no, I'm not going to manage TODOs on my phone - whole other conversation

I will. Far simpler, far more secure and far less wasteful than inserting some additional and unrequired LLM loop + hardware/virtualisation layer on top to do something I've already been able to do for years.

> But until you've had it on you for a while, you can't comprehend the utility.

You've not yet described anything that literally 99% of the population can not already do with the existing hardware and software in their pocket.

> Far simpler

And far less capable. I have a whole system for managing TODOs, notes, etc, and I've not found an app that fits my needs (especially given that the system evolves over time).

But I agree - if you have a flow that works great for you with just a phone, then I wouldn't recommend OpenClaw for that use case.

> You've not yet described anything that literally 99% of the population can not already do with the existing hardware and software in their pocket.

And in the early days, literally everyone I knew who owned an iPhone also owned a digital camera and a laptop. Why pay some crazy amount for a fancy phone?

Well, i'm happy for you from the respect that as someone with ADHD, getting a working notes and TODO system for me was life changing, and was something that in fact took me years, and I still tend to occasionally uproot my system, so I can understand that getting to somewhere it works for you can be of tremendous value alone.

> I have a whole system for managing TODOs, notes, etc

So do I and it can already accept input via text or voice from my phone and so I’m just not seeing the benefit of inserting an additional LLM orchestration layer just to route tasks into it.

> And far less capable.

My current setup can already capture voice and text, and can route it automatically into Logseq, Trello, or even org-mode. These all can be viewed from the same (or other) devices. Honestly, I would have to think it was of more usage in retrieval than submission if I was to ever go that route. Like instead of reviewing my todos/schedule manually.

> And in the early days, literally everyone I knew who owned an iPhone also owned a digital camera and a laptop. Why pay some crazy amount for a fancy phone?

A Phone enabled entirely new behaviors that were not possible from my laptop or camera at the time. Persistent connectivity, real-time location services and on device image capture, edit and sharing just to name an incredibly small few. It created use cases that weren’t practical or even possible previously.

I’m open to being convinced, but I haven’t yet seen an example where OpenClaw enables something meaningfully new rather than repackaging something I can already do right now. Perhaps i'd be more open to it if it not literally everything I could think of using it for did not lead to atrocious security implmentations.

> A Phone enabled entirely new behaviors that were not possible from my laptop or camera at the time. Persistent connectivity, real-time location services and on device image capture, edit and sharing just to name an incredibly small few.

All of these things were doable without a smartphone - just very inconvenient to do so.

And all of these things are potentially dangerous ;-)

> Perhaps i'd be more open to it if it not literally everything I could think of using it for did not lead to atrocious security implmentations.

I was like you - seemed too scary (and expensive) to use. But given its traction, I figured I may end up at a disadvantage if I didn't at least learn it. So when I had some time, I simply looked at it, felt installing a VM is (relatively) low risk, and tried it out.

It's a very open ended tool. Ideas will come as you explore its capability. When LLMs came out, people (including me) said "Neat gimmick, but is it actually useful?" and stopped using it a month or two in. It was about 6 more months before I found a real use case for LLMs, and slowly I found more and more use cases.

And so it is with OpenClaw. For me, just being able to query it for the exact weather information I need is great - if you live in an area where knowing this stuff is important.

I have yet to find a tool that is good in converting receipts into the form I need. I spend time each month doing it manually. LLMs may get me there, and if it does, I'll likely hook it into OpenClaw.

ADHD here too

For me what works is limiting and filtering everything. I'm a programmer so I write small tools for this, CLI-ones because they have the lowest barrier of entry for me and are also scriptable - and nowadays LLM-capable.

At work I get a bunch of Github notifications from all kinds of crap, on the Github site the options are "on" and "off" pretty much.

So I built a TUI tool that uses the `gh` CLI and filters out all that to just the exact set I want to see, nothing more.

I have a tool that summarises long Youtube videos for me in a way that I can quickly see if it's worth the 40 minutes to 2 hours of watching or is it just two ideas spread over multiple minues for more ad revenue.

Pretty much every operation that needs me to pick up my phone, unlock it, find an app and in the app scroll down somewhere to get to the information will eventually get a CLI tool instead. Gonna do a weather one right now just based on @BeetleB's idea :D

And I'm pretty sure by the end of the summer I'll have some flavour of Claw running and using those tools to proactively give me the information I need.

A simple example: Calendar has an event far enough to warrant driving -> claw checks weather around that time+location(s) -> notify me if it looks like I need to dig my car from under a snowbank again. Or at the very least ping me with the current + future weather prediction around that time.

Yeah, automation sounds good in theory, but you need to set it up, then it fails, and you need to fix the edge cases, maintain it. Even with OpenClaw, it still fails my daily briefing from time to time, and I keep debugging it, which isn't how I want to spend my time. At least with a bot I can keep asking it to "fix it"

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

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.

Thanks for this! I completely get how these "claws" work and have a few... they're super useful for specific things. I’m simply curious about the accurate or, more importantly, adopted terminology, as I've dug rather deep and have yet to find anything concrete. "Claw" it is...

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.

Have you experimented at least with running Claude (or whatever) as a cron-job? I'm seeing a lot of things emerge from just that pattern alone. I'd recommend giving Claude a way to communicate with you if it has issues to raise though, even if it knows you're asleep.

I'm not running OpenClaw either, but I'm getting a ton of value just from my homebrew deterministic "run while loop, wake up Claude if trigger event occurs".