But every single use case I've read so far could be done with a pretty affordable SaaS product, Zapier, Automator (app on a mac that's existed for over a decade), or something simple you could make yourself.
It also feels like people are automating things that don't really need to be automated at all (do you really need to be reminded to make coffee?)
I fully realize this is probably me being a curmudgeon, however, I have yet to see someone make an actual, practical use case for it. (I would genuinely like to know one, I just haven't seen it)
Two decades! It will be 20 this April.
https://en.wikipedia.org/wiki/Automator_(macOS)
Though technically it’s deprecated in favour of the clusterfuck of bugs and limitations that is Shortcuts.
But you’re right, OpenClaw seems to be another fad being used mostly by “influencers” and “thought leaders” to show how awesome and productive they are at… Writing blog posts about being productive. It’s the LinkedInification of the web. What matters is the signal that you use the tool, not that it does something truly useful.
It's been almost five years since Apple announced Shortcuts for macOS and the start of the "multi-year transition" from Automator, but I feel like Shortcuts for macOS has not gotten any better in that time.
I'm guessing a lot of that is built in to photoshop now, but I have always been surprised how few people seemed to use it with how much it could do.
I'm convinced apple doesn't want people doing general purpose computing on their apple devices.
they even want developers going through their gauntlet of apple-invented languages*.
[*] or NeXT
Once you get the dopamine hit of having an ai assistant do something in the real world it becomes an hammer you want to use on everything
Instead of being a problem solver you start to become a problem hunter, and you invent them in order to solve them
Generic problem of any Linux newbie. You get good at solving problems and it's so enjoyable so you end up creating more of them.
IMO OpenClaw or a similar agent will be on everyone's phone in a couple years. It's basically what Siri was always supposed to be. For the average user it's obvious that this is the way computers are meant to be interacted with.
Almost every time I have an idea for AI Agent, I end up just making a script/binary that does the same, but so much faster that adding AI to it feels silly.
Recently I made a tool router that runs locally for such tools. Some tools have no arguments at all. Claude created a quick overlay where I can text/speak, and it will do tool call, without me asking for it, Claude added 4 buttons next to text input that bypass agent and just do a "tool call". I barely use text-to-command because those 4 buttons cover 9/10 of my use cases.
At this point I'm trying to come up with tools to add to it, so it's actually useful as an agent. Almost everything ends up being a cronjob or webhook triggered thing instead.
I often quip that I became a programmer specifically to avoid having to use spoken language. I always twitch at the thought of using any voice-based assistant.
Thinking in systems and algorithms is more enjoyable than using human language when it comes to computers IMHO ...
Dangerous? Yes, very, but it truly feels like living in the future. Surprisingly, it's even more fun that sci-fi movies made me think this would be.
I was having a conversation with someone about OpenClaw, and they proposed this idea of OpenClaw being used for inventory tracking at the retail-level. I let them continue. They said it'd be the best option for tracking when purchases are made and what SKUs are sold at what time of day. They weren't talking about prompting, they were talking about it as a data store.
I didn't bother mentioning how long this problem had been solved.
It's not you being a curmudgeon.
The ironic thing here is that the person could go to ChatGPT (or whatever), describe the problem they're looking to solve, and ask it to find them the various ways it has been solved reliably (with links to the sources to confirm the information). And even provide some details on when each solution works best and why.
Because THAT is a great use for AI.
I've posted about this before, I call it the Jarvis effect.
> For years we had people trying to make voice agents, like Iron Man's Jarvis, a thing. You had people super bought into the idea that if you could talk to your computer and say "Jarvis, book me a flight from New York to Hawaii" and it would just do it just like the movies, that was the future, that was sci-fi, it was awesome.
> But it turns out that voice sucks as a user interface. The only time people use voice controls is when they can't use other controls, i.e. while driving. Nobody is voluntarily booking a flight with their Alexa. There's a reason every society on the planet shifted from primarily phone calls to texting once the technology was available!
By and large the reason people love Openclaw is that it feels cool and futuristic. You have an AGENT! It's DOING THINGS! Yes it's doing things you could have easily done yourself, but you're not doing them yourself, you have an AGENT! It's all very silly, the same way that having your lights controlled by your phone is very silly, but some people like it.
That being said there a real use case for Openclaw, which is "marketing" (aka spam). A ton of people have set up Openclaw agents which exist to post on Twitter/Facebook/Discord/any open public user discussion forum (yes, HN included) to seem like a real member of a community, then start advertising something, generally crypto. So we can thank Openclaw for dead internet accelerationism.
In 1996, I picked up the phone on my desk, dialed a 3 digit code, said “I need to fly to Los Angeles on Tuesday morning, returning Wednesday evening”. A couple hours later, an envelope appeared in my inbox with plane tickets, rental car reservation and hotel reservation.
Then every company in the world fired all the secretaries over the course of the next few years to cut costs, and we’ve collectively forgotten that it was ever like that.
With a mouse and keyboard I can switch windows.
With my voice, the computer can’t yet automatically determine if I am dictating a transcription or giving editing commands. What I really need is the interpreter listening to me to intuitively to know whether I am in the equivalent of VI command mode or insert mode.
It is the roadblock to not needing a screen at all, right now I want to visualize whether it understood me correctly because if it didn’t switch from insert to command automatically, I now have all my commands written into my paragraph. I also don’t want to listen to the computer talk back to me to confirm it listened. I want to just keep going, to keep narrating my thoughts and trust it’s doing the right things, not having to check. Having it slowly chime in to repeat that it listened derails my flow and train of thought.
TLDR The future of voice is headless vi.
Ah, so that is indeed the endgame of what I've been seeing, hmm?
The stuff you've listed are the kinds of things smart home enthusiasts do with whatever tools are available to them, and are just a sign of people exploring the possibility space.
Is my OpenClaw agent currently changing my life? No. It sends me a morning briefing based on my calendar, the weather, my Readwise highlights, and notes on who I'm talking to today based on call transcripts. I use it as a food diary (which I could have done on platform LLMs but this feels like a more personalized UX as we can write the logs to text files on my personal computer). I can absolutely see how transformative this agent can become in the next few years. Certainly my usage of LLMs has changed my life since ChatGPT first launched.
You are seeing the loudest / most hyped users. There's a reason it has so many stars and most of the people getting something out of it are not posting on X. They're just using it to do the thing.
That reason is buying stars, agent swarms, and astroturing.
No project gathers 200K stars genuinely in 3 months. There are far more useful and popular projects that need 10 years to get 200K stars. When you see a project like this get 200K stars in just 3 months, you know something is very fishy.
https://www.pcmag.com/news/meta-security-researchers-opencla...
Maybe OpenClaw was just practicing a really aggressive form of Inbox Zero.
However, it seems better if you could, as much as is possible, move the AI stuff from runtime to “compile time.”
Instead of having the AI do everything all the time, have AI configure your Zapier (or whatever) on your behalf. That way you can (ideally) get the best of both worlds: the reliability and predictability of classical software, combined with the fuzzy interface of LLMs.
Like if you could just sit someone down for 30 minutes and show a few "power user" things, you will have truly taught her to fish for a lifetime. But it can go so unaddressed, and people's careers are built on these small ignorances.
I've cancelled everything at this point and just call Emacs my "special agential assistant," it makes me still sound in-the-know, and most of the time no one knows the difference!
"Convenience" in this context is laziness; "productivity" and "efficiency" is for management and bosses. We don't need to be our own bosses, I want to be free from such things as an individual. I want to be capable, be maybe almost "cool." Its sad to see a whole generation turn into such product dorks!
"Oh please read my email for me Mr. AI!"
I know about those tools, and I'm always in the mood for automating thing... and yet I don't use them.
I'm not yet running a Claw because of the prompt injection / lethal trifecta risks, but I absolutely understand the appeal. Reducing friction to automating stuff from "figure out Automator again" to "message your bot" is a material difference.
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".
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
Is there something I'm missing about March or is it just a diverging reference? If the wave of non technical folks being able to automate new things is here, what's the equivalent impact of that? Maybe this is the inflection point where everyone needs more tech support like some sort of post Christmas surge? Maybe less because they have the tools to help themselves without trying now?
I'm not sure we're there yet anyway; I think this is still first adopters and enthusiasts. I asked my wife and some non technical friends and none of them have heard of openclaw yet. I think the deluge will happen if Apple or Android bakes it in or one of the big ai companies makes the app good enough for a normal person to unleash it upon their life and community.
I'm currently in founder mode and building two projects in Mexico. Finding the right real estate is in the critical path for success of the project. It's really hard to find quality real estate agents or brokers here and not because they don't exist. We have thousands they just never follow up with you or give you any updates. So, I'm using OpenClaw as my real estate agent that uses WhatsApp as a communications channel and manages the entire pipeline of first contact to scheduling a visit.
Right now, I feed it images of postings that I see on the street and OpenClaw handles everything else.
It really depends on where your personal or professional bottlenecks are and if you're running a business this project is absolutely amazing.
Im really not sure why this has to be said again and again.. it seems humans just don't learn do they?
Im waiting for someone to show me something that starts with the experience and then explains how the LLM fits in. Not the other way round.
I think because Google Search is predominantly tech-based, it is easy to see why LLMs have impacted the way we think about the experience associated with Search over large spaces of information.
Beyond that, Im not seeing much.
For example, I've never heard of Automator. I'm familiar with Zapier, I'll have to evaluate the two situations, then I'll find out that might need to find an alternative that runs on Linux and then I'll have to check if....
These are all simple steps but they all use a non-trivial amount of time for the problem their solving
The other thing is the
Have you tried to run openclaw? Their own docker container (apparently a compose now (???)) doesn't work for half the versions and the docs are probably the least informative thing you'll ever read.
I would venture a guess signing up for Zapier is easier than getting OpenClaw up and running. Who can get a container running on a Mac but can't sign up for a SaaS product?
I assume a lot of these folks were already using LLM's quite a bit, but were using the Chat interfaces or had workflows that were split among a bunch of different services and tools. Something like OpenClaw gave them a way to centralize a lot of that and also gave them a way to use natural language to direct efforts. So for them this probably feels like a big step change.
If you are coming from a programming background you were aware that this type of setup has been doable for a while, but you were probably content sticking with Claude code or similar tools because those tools covered most of your LLM based workflows quite well.
And tying this altogether, one of the lowest hanging fruits for content creators is to create content about the tools they are using. Doubly so if that particular tool is starting to go viral. So you end up with a self feeding virality of sorts, as OpenClaw got more popular, more content creators started using it, and then publishing content about it, etc....
I never said OpenClaw was a bad idea.
I said the way most people are using it now isn't practical and/or saving them any time, and if there were ways, I would love to hear about them.
This is part of why the whole discussion has been so low value: people always default to "yep you're going to be proven wrong one day" or "you'll just be left behind then" instead of showcasing an actual, real life, practical example of using it to be more productive.
If you think it's fun and enjoyable, then have at it. I'm just not the biggest fan of people wasting a bunch of time on novelty and then telling me I'm dumb for not doing the same.
There’s loads of good discussions about local LLMs in this thread:
That can't be allowed, and also won't happen. If token costs do start going up at a serious rate in the US, you can be sure that they'll stay down in China, and the political situation won't allow for the inevitable exodus to Chinese providers.
I don't want to learn N different SaaS products (nor worry about them changing their TOS, going away, etc).
To be blunt, if OpenClaw were reliable, secure and affordable, lots of SaaS products would simply die. Why spend the time learning all of them when I can just tell the assistant what I want?
> or something simple you could make yourself.
That is OpenClaw at a higher abstraction! Instead of me sitting typing, or babysitting Claude Code, I can just tell OpenClaw what I want and it makes it for me.
(When it works, that is).
Like other people have said people are having fun with their computers; that’s why it’s popular. That’s also why a bunch of people on forums throwing their hands up and saying “I don’t understand it. Why don’t they see that there shouldn’t be any fun whatsoever?” is not really a deterrent at all.
It’s also why it doesn’t matter that the categories of tasks they are doing can also be done with a whole set of tools that are no fun to use.
The market will eventually realize the business case for an OpenClaw-like product, and I'm waiting to ride its coattails!
Eg. tell it to book a flight ticket for X without dealing with "modern UX" and 1GB websites
I installed picoclaw on a whim (or nano? can't remember).
In maybe 15 minutes I had it make a "get weather for this specific area using the met.no API" skill and "check the train tables at these two stops for this specific line" skill.
Then I could just say "I go to the office every Monday on a train that leaves at 8, notify me if the weather is bad or there are delays in the train schedules"
And it just worked.
The "make a skill" bit was optional, it could've figured out both on its own, but I've been doing this for a while and figured out it's a lot more (token) efficient to have it specifically know how to do the things I want it to do.
---
Now lets take this loop and think about the system and what it could do.
Even if I wasn't a programmer and just went with "tell me when the train line I use for my commute is late" the system itself could see that "hmm, this looks like a thing I'll be doing often" and create a script/skill/plugin to do that via an official API (or WebMCP in the future).
You can't do that with Zapier or N8N.
There are many cool ways a pure LLM-powered system like that can be optimised, and more importantly, can be taught to self-optimise. By default I think the systems use the "main" model to read the HEARTBEAT.md file, which is stupid expensive. That could be done with a local model small enough to run on a modern phone.
And if that small local model says "yep, there's something to do", then it can either give the full task to a LLM or if it's smart enough it can spread specific tasks to small or medium local models first.
tl;dr OpenClaw is what Siri should've been after that epic fail of a Apple Keynote.
reminds me of those "zune already does everything ipod does" posts.
This applies to *clawphiles just as accurately.
I built clawr.ing so my agent can call me on the phone for urgent things like emails I’m waiting for or issues in production for any of my products
all the things I do with openclaw are in that ballpark of usefulness/importance.
I just don't get all the hyper either. I think it's because people just create automation workflows by typing them out rather than being in the trenches.
What are you talking about? In openclaw you literally type out basic English instructions to an agent. This isn’t painstakingly setting up chron jobs and writing scripts.
I have an OpenClaw setup with a Claude API token and Qwen local model, running on an M4 Mac Mini with 32GB RAM.
1. At 7AM and periodically throughout the day it checks my calendars (work, parenting schedule, personal), a hyper local weather station, and some specific news topics — and sends me a summary and throughout the day updates if anything significant happens.
1b. It also sends this to my TRMNL e-ink display.
1c. It can also add and edit calendar invites, so if I want to move my yoga I can just tell it to move it to whenever the next yoga class is at (it knows what studio I go to and figures it out)
2. It has a skill I built that acts as a second brain for knowledge. I can send it Fitness Youtubes, parenting/health research papers, podcasts — and it organizes, summarizes and saves it in a logical file structure. Then in the future I can access these. It's like bookmarks on steroids. I love it for 1-2hour YouTube videos where I want summaries. It also pulls out any books any artifacts mentions and generates me a rolling reading list. https://plc.vc/npw
3. It has its own email address — and read access to my personal email — so friends can email it to schedule things like evening video game sessions. Similarly, if I get an urgent looking email it'll provide it in #1. I don't check my personal email aside from via OpenClaw.
4. It has read/write access to my GitHub, and each project repo I have has a well defined Claude structure, so it can make changes, commit the branches to Fly.IO and send me domains to test things. I love it for esoteric tweaks to my blog.
5. It has access to my Apple Reminders so I can message it things like "remind me to buy more muffins" and it has context to know to add those muffins to my Costco grocery list not Trader Joes.
6. It runs a headless browser, so when my hyper local weather service (Bouldercast) sends a summary that has more detail behind a login, it can open the email, click the link, login with my credentials, summarize the forecast, and send it to me.
7. It drafts blog posts for what it did for me each week. It's fun! https://plc.vc/d5t
I am a previous Zapier power user. I have used their LLMs, databases and Zaps extensively for the past decade. I understand the scorn towards AI, and I understand that if you look at this list you might think that it's either trivial tasks and/or things that could be done with Zapier, but I have been _amazed_ at how effortless it is to setup.
Similarly, I love that I can on the fly improve this assistant — last night I told it "I want to extend our Knowledge skill so that you can subscribe to RSS feeds and summarize articles in my knowledge base and also deliver interesting content in my daily summaries. Update the knowledge skill and our tasks to do all this."
It one shotted that, simply asking me to provide the first RSS feed I wanted to subscribe to.
It's genuinely like having a human assistant that happens to be an expert coder/technologist on call 247 that works at the near speed of light.
It disappoints me that technologists are so skeptical of this technology rather than exploring what it is and why it might be different to what exists today. It's fun! thats the takeaway: it's FUN.
It's most likely fun for you because it's novel, and for a lot of skeptics, AI novelty has long worn off.
Really makes you think about what makes products good
React and Linux got their 200K stars slowly but surely over 10 years. OpenClaw got their 200K stars in like 3 months! Is this any meaningful comparison?
Getting 200K stars today doesn't mean much because today stars can be bought. There's a big shady thriving business of selling stars. Stars today can be generated using swarm of thoughtless agents. What's the use of counting these stars when they don't mean anything anymore?
Would be nice to see a graph of stars by account age, how many of the stars come from accounts that are under 6 months old for example?
Compared that to the people who have been starring my projects, and every single one of them had some sort of activity on record.
--edit--
Checked again now, seems more recent accounts have some activity. But still, lots of accounts like these
Starring can be useful to the starer. They are just counted because it is countable. Whether you find the number meaningful remains up to you.
Let's wait for the explorers to return.
Full story: https://brtkwr.com/posts/2026-03-02-upgrading-openclaw-to-la...
I'm also curious if it's particularly wise to have a web-facing system running on software that hasn't had a security update in 3 years?
But wouldn't have been quicker and simpler to add ".bun/" to the pattern of authorized paths the same way it presumably works for ".npm/"?
> Starting around OpenClaw 2026.2.26, the project tightened plugin manifest validation. Manifests outside expected trust boundaries are now rejected as unsafe. On my Jetson, Bun’s global install layout (~/.bun/install/global/node_modules/...) tripped those checks for every single plugin
React has been around for over a decade, and in that time pretty significantly impacted web dev paradigms (along with a few other mediums).
It’s hard to imagine being a web developer today and not knowing at least some react.
OpenClaw has been around for like a few months? And maybe it’s on its way to having that sort of impact? But right now seems to he mostly the purview of very early adopters and AI influencers.
It's popular because people are exploring "what can i do with compute" once again. React is as meaningless as tickless kernels for vast majority of people.
Should be noted that i am not using any claws. Just a person remembering people spending their nights programming all sorts of psychedelic displays in qbasic with some moving on to asm. Asm for fun.
It's larger than literally every open source service I thought to use as a benchmark. Rust, React, Vue, Symfony, Laravel, PHP Stan, Python, ESlint, rails, LLVM, Spring, fucking Linux itself.
I would wager the legitimate stars for OpenClaw are single digit percents of this. But hey, I haven't actually run the numbers on the GitHub API.
If we had a decent technical universe much of this stuff would work in ways that simply don't require LLMs for anything other than the initial setup.
I picked Whatsapp but it ended up using my own account! So it's absolutely too dangerous. We are supposed to create a separate account but with which phone number? I only have one.
So I picked Telegram instead, added it to a group chat, but it was a slog to set the authorizations.
In the end I don't trust it to read my mails for security reasons so I uninstalled it!
You're joking right?
Just like Jetbrains gives away IDEA licenses for open source projects, you need to have some metrics go up before they even consider you.
"If dev null is fast and webscale I will use it"
"Does dev null support sharding"
Who remembers https://www.youtube.com/watch?v=b2F-DItXtZs
For example, someone working in safety and alignment at Meta: https://nitter.net/FakePsyho/status/2025857836014538818
There are so many mails and communications with so many tasks to research via confluence etc
But on my private hardware? Idk, I haven't found a use for it...
Email is stored in your device somewhere, you could just get its content sent to your preferred agent, you can use one of the many mobile clients if you rather interact through that kind of UX (like self hosted hapi.run + tailscale for example), and you could setup a cronjob or something like it on your machine to do it based on whatever interval. This is just one way I personally could go about it, YMMV obviously.
Is there a specific reason why you will not do something like that for example?
For those who use Claude (or similar LLM APIs) on a daily basis, what does your monthly spend look like in practice? And do you feel the cost is justified by the value you’re getting?
or is it tooting its own horn?
I avoided the hype at first; however, it has become extremely efficient for emails and notes, and I can see how this can extend to any sort of digital workflow. The convenience of chatting with this thing, no matter where I'm at, is a key marker.
I’ve tried OpenClaw two weeks but don’t know what it can do for me.
I let it to finish some project for me, but the most hard work for project is validating the results over giving instructions
https://github.com/pjasicek/OpenClaw
OpenClaw - Captain Claw (1997) reimplementation
[1] https://news.ycombinator.com/item?id=3742902 [2] https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
What's so good about that?
React popularity is also a phenomenon closely tied to popularity of the fb
I set it up, and had it do a few things, then decided its too risky after seeing some of the drastic failures it had caused some people.
Sure I understand you can sandbox it and all, but even then I couldn't think of much stuff I wouldn't want to do myself just nor justify the cost to run it.
It's neat but the token use is pretty inefficient and security of course is a mess but it's been fun to play with.
I am messing with NanoClaw now and it's pretty much the same but only support Claude (uses code to do everything)
It's weird that most people in these comments are speculating fraud.
Why aren't companies with real money to gain from stars gaming the system to the same degree? Why do the other metrics - issues and pull requests - match up with its popularity? Why would the bots starring the repo mean that those same bots are not popular? Those bots are controlled by their users.
The project is extremely active because this is what everyone being able to customize their computing looks like. A mess.
But it's a good mess.
Github was the old code sharing model clearly not designed for this. I'm sure a new model for code sharing will come to fix the growing pains.
A ton of people who would have never been able to customize their computing experience are finally able to. And it is magical for them.
This means that those same people will finally value having access to source and use of open protocols.
It was always valuable to us because we had the power to make it matter. It never mattered to them because they did not. Now they do.
The last era of computing was defined by dumbing down computing for the masses. Less information, less customizable, and more metric driven. Control in the hands of the companies.
This new era will look more free/libre, more personal, and less enshitified. Control in the hands of the users.
This is a very positive development.
How are you gaining money from stars? Why would Facebook bot stars for the react repo?
Why are people so keen to let a company get that close to their real life’s, it’s terrifying!
Steinberger and his VC club on Twitter were so salty about HN not understanding his grand creation that something needed to be done.
But that stargraph is ridiculous .. absolutely crazy
Come on HN.
That's a surprise.
But suspicions on the legitimacy of the stars seems reasonable, wouldn't you agree? Look at the rate of stars, look at the comments/issues/prs on the repo. It feels safe to assume that most of them are from bots and not organic humans who went out to star a cool project.
This is the lowest, most boring form of programming.
"My React website can't star React"
"in what sense is this software not a virus?"
"GitHub stars are great for measuring the number of GitHub stars a project has"
etc.
All gold.