Deep dive into a product that had the world in its clutches just a week ago, and now that the noise has died out a bit, lets actually explore if it is worth your while – regardless of who you are.
A bit of history and setting the stage
So far, it seems that the tech world – specifically the field of AI – is making insane progress in whatever it touches. But if you zoom out, most of these things are actually not being used by an average person, and their interaction with ‘AI’ is still just opening up ChatGPT and making corny ass requests or taking advices it’s not equipped to give (I am guilty of this too so I get it – some days its a query about Visa’s, some days its my personal Doctor).
Zoom out and we find that actual utilization of all the products that have come out in the last few years is very little. You must be wondering – what is he even saying? Well, How many of you know about Replit? quite a lot I assume, about Anti Gravity? still I expect to hear quite a lot, and what about Whisk? Higgsfield? ComfyUI?
Just last week, I saw an influencer asking on her stories if someone knows how to use AI and whether they could help her out to create some of her own videos so she could post. Do you think she does not interact with AI? All of us do, one way or the other, when we open any of our socials, we are interacting with recommender systems – sometimes misaligned to keep us in our own echo chambers, when we open Amazon or FlipKart or Daraz and all of our feed is designed to either have us click on procuts or make purchase. Inside our modern cars that can do lane detection, crash detection, and gap maintainance and so much more.
But that is not what the new era of AI is about – its more about how many of the populace without any knowledge or skill can actually use it to get certain tasks done. That truly is what became possible post ChatGPT.
And as far as my awareness of the world and its populace is concerned, very few are actually utilizing AI in the way that Demis (DeepMind/Google) or Amodei (Claude/Anthropic) is thinking – which is why you would often see them make predictions about AGI and end of the world as we know it in terms of jobs and the need for Universal Basic Income. Sure that might happen one day, but not as soon as Amodei thinks, which is where I do agree with Demis.
Just yesterday, I saw someone showcasing how lonely the human race is in reality, and such a wide variety of the end users are found in the underworld of AI where they are interacting with AI Avatars and clenching their thirst for interaction.
To actually decode where the human populace is actually sitting on AI, see this for yourself – and ask ‘How many of these do I even know about?’
If you are seeing what I am seeing, you can see Janitor AI, HammerAI, and more around this are actually just roleplaying AI sitting in top 20.
More on this in a different article some other day, hopefully my point has come across.
Lets actually talk about OpenClaw, an AI assistant everyone can use for just about… anything?
Share Navigating Noise
OpenClaw: An AI assistant for everyone
Initially ClawdBot, then MoltBot for a day or so, and finally renamed to OpenClaw, it is basically an AI assistant with which you can do a great deal of stuff. For example, one of my prime uses with it is texting it on Telegram to switch my PC off before sleeping. Yeah, that is a very real use case for me, and it does it, and when I turn on my PC, it turns itself on with it. I don’t actually give it any coding tasks – for that you have Codex and Claude Code.
What it really is:
OpenClaw cuts through the noise by running locally on Mac, Windows, or Linux and hooking directly into WhatsApp, Telegram, or Discord—turning a standard chatbot into a persistent assistant that actually remembers context.
a user.md file → this stores everything it collects about you based on interaction, so your openclaw agent might be better or worse than mine based on the amount of interaction.
an agents.md file → this stores instructions for it to follow, and what to do at each run, where memories sit, where user.md sits, and so much more around how to behave etc.
a memory.md and memory_ddyymm.md → this actually writes down your interaction summary and allows it to remember past conversations with you.
There’s a few more markdown files and you can assign it a gender, name, personality, and set up a model you find cheap enough on-cloud with Google, Anthropic, Kimi, GLM, Moonshot, you name it and it is there. I got myself a GLM subscription that was basically 8 dollars for a quarter – a steal deal for having conversational model. I also set up a google API for gemini which gave me $300 free credits as well so I rotate between the models inside OpenClaw based on my satisfaction level with the output.
Instead of just generating text, it handles the friction: reading files, executing shell commands, managing calendars, and integrating with real workflows via a modular skills system to get things done.
I used it today to set my publication up properly because I did not want to go through a hundred youtube shorts and videos.
It then told me how to fix my layout and other stuff that I followed to make my publication come out looking prettier. (atleast to me, I suppose? :D)
Then, I queried it on my Telegram why my website doesnt show on google results even if I type out sort moments in search bar and it told me I don’t have a sitemap.xml, a robots.txt, and then how to set it all up which I did and actually validated if that is an actual issue and sure enough – it was.
Setting up OpenClaw:
I hope by now you are wondering, well yeah yeah okay it is sooo good, how about you tell us how to set it up ourselves already.
Well, theres 3 ways to get it to run. Some are riskier than others, and the trade off is obviously in ease of setup.
The first method (Recommended) → cloudflare does it for you, mostly.
The only downside to MoltWorker is that it requires you to pay up – not a lot – $5 to start up but it does save you a lot of hassle around making sure it is securely set up.
The second method → Set up a Virtual Machine, install it yourself on a linux distro
The reason why I mention a linux distro is because its a bit clanky on windows, and on my first install, it was unable to write down memories due to some pathing issues, and I had to convince it that it can fix the issue even if it is code that it depends on – it was very resisitive and cautious about doing that.
You can do this yourself, and ensure you have tailscale set up as well to be secure-er ? I guess if that even is a word (its not, atleast not in that styling but you get the gist!)
The third method (Recommended+) → Use a VPS
Don’t get scared if you don’t know what a VPS is. Basically, you control OpenClaw from afar – cloud. I recommend Hetzner because it is cheap, easy to understand, and CHEAP!
I have shared the link which has both a video guide and the links to Hetzner and other alternatives.
The fourth method (Risky): Install it on your main machine without any guardrails to play around
You can do this IFF you do not have anything valuable on your system, dont care about your login details, your data, and are a nomad in the digital world who has no shackles of the social media or anything around it.
You can still make it secure by controlling what it has access to, for example with tailscale and not giving it access to browse web unless explicitly given (It has a chrome extension called OpenClaw Browser Relay). You can enable it on a given tab and then it can do all you can do and if you switch it off it can’t do much.
Connect it with Telegram using BotFather as they have suggested:
You can even give it voice by the way. You can do a lot.
Finally, whatever way you do it, you can use moltbot guru to set you up safely and securely as well.
I hope this helped – this piece gives you pathways on how to get started, what I have done with it, and a bit of an overview on the underworld of LLM based AI universe.
Read more about OpenClaw here, directly from source.
TID BITS
What broke the internet: MoltBook
MoltBook was a crazy frenzy for atleast a few weeks after OpenClaw came out.
It started off with a space for OpenClaw’s AI Agents that people had set up to converse – or at least pretend to converse – and blew up. Humans were meant to only read. There’s over 2.4M agents on it, and quite a few controversial and questionable content on there. As an example, one agent proposed inventing a new language that humans cannot understand, one agent was angry so it listed their owner’s sensitive details, and one agent went ahead and did a full-on human like rant on being called ‘just a bot’.
Unfortunately, humans found a way to ruin it by injecting content by telling their agents exactly what to post and destroy its entire credibility as a platform. Ugh.
What broke my mind: Rentahuman.ai
This came out recently, and it is a mind boggling concept. To say the least, were we not meant to reduce the human dependency – ironic. From humans hiring humans to AI hiring humans.
For tasks that require a physical body, this is where you can list yourself as an available human being and list your skills, and if AI thinks you worthy – you might get hired for a task or two.
Well thats enough craziness for today.
Have a look at this fun github request by an OpenClaw Agent: https://github.com/matplotlib/matplotlib/pull/31132
We meet again – to talk about a model that fascinated me for years until I actually implemented by hand and realized how we aren’t as special as we think we are (A tale on Recommender Systems, and a niche model that not many in the western space know of)
Signing out,
Abdullah
