OpenClaw And The Future Of Personal AI Agents

0:00Today I'm sitting down with Peter Steinberger, the creator of OpenClaw, the open source personal AI agent that has completely taken over the internet. The GitHub repo exploded to over 160 ,000 stars practically overnight. The community has built countless projects like Maltbook, where bots talk among themselves. And now, the bots are even renting humans to do tasks in the real world. In our conversation, we discuss his aha moment, his contrarian development philosophies, and what this means for builders in 2026. Let's dive in.

0:38So good to see you, man. Hey, what's up? So you've made something people want. It seems so. Yeah. Open Claw, as it's called now, has absolutely... Name number five, yeah. Has been absolutely exploding the internet. How have the past one or two weeks been for you, man? Oh, my God. I need, like, I need a cave. A week of solitude. You came out of the cave and you want to go back to the cave like a little officer. It's been absolutely wild. I don't know how one human can absorb all of that. I probably need another week just to like respond to all my emails. I got some incredibly cool stuff. I got some incredibly bad stuff.

1:20But clearly I hit something that spur up emotions and made people interested and inspired people. That's really cool. And a lot of people have been working on, you know, AI and even personal assistants. Like what is it that made Open Claw take off? I think my big difference is that it actually runs on your computer. Like everything I saw so far runs in the cloud. It's like it can do a few things if you run it on your computer. It can do every effing thing, right? So that's really more powerful. Yeah, the machine can do anything that you can do with the machine. It can just connect to your oven or your Tesla or your lights, your sonos.

2:03My bed, it can control the temperature of my bed. ChatGPT can't do that. You gave it all the skills that you have yourself. A friend told me he installed OpenClaw and then it asked him, like look through my computer and make a narrative over my last year. And it made this incredibly good narrative and he was like, how did you do that? And then he, the OpenClaw found audio files where like every Sunday he was recording stuff and OpenClaw found that. but he didn't even remember about it because it was like more than a year ago right so so just by it being able to search a whole computer it can surprise you yeah it's also you also give it all the data right so it can surprise you in many ways and so now you have you know we're even moving from human to bot so like interactions that you've been talking about to bot to bot interactions or even like bot to other humans where you know bots on behalf of you are then hiring other humans to accomplish tasks IRL like what's happening I think that's a natural next step like okay I'm gonna book a restaurant my bot will reach out to the restaurant bot and do the negotiation like because it's more efficient or maybe it's like an old restaurant so my bot needs to actually get some some human work done so that the new one then calls the restaurant because they don't like bots or walks there to stand in line if he doesn't get a robot for the owner of the bot and i imagine that like maybe if if i have even multiple bots and maybe i have like specialists one is like for my private life and one is for like my person my my work stuff maybe one is our relationship bot that cares like everything's in between uh i don't know we're so early.

3:58There's still so much, so many things that we haven't really figured out if it actually works. But I feel we are on the timeline now. It seems like everyone was chasing sort of like the centralized god intelligence and was sort of emerged over the past you know 10 days or so. It's sort of like the swarm intelligence and the community intelligence. I think that if you look at one human being, what can one human being actually achieve? Do you think one human being could make an iPhone, or one human being could go to space. One human being would probably just not even be able to find food. But as a group, we specialize.

4:41As a larger society, we specialize even more. So what can we learn from that that we can apply to AI? You know, we already have AI that specializes in certain things. even though it's generalized intelligence, what if it actually is also specialized intelligence? So I know it's going to be very exciting and cool. Yeah, you kind of like opened a window into the future and now a ton of people are kind of like building on it and have sort of like their aha moment. Can you walk me back to when you had your aha moment and kind of like recount that very moment? I wanted something to like just type stuff so my computer would do stuff.

5:20like very simple and then I built a bit of version of that in May June that was cool but wasn't really yet and then I built a whole bunch of other stuff and kind of like build up my army and then in November there was a day where I wanted this again like I I went to the kitchen and all I wanted was check up if my computer will still do stuff or being finished and doing stuff was was coding you were coding stuff yeah of course were you coding something else or were you coding the thing itself no no that was just like the need was again there and I'm like what were you coding at the time were you building my god you see my github is like it's like 40 projects I don't even know I think it was summarize it's like a it's like a little CLI app where you can give it whatever like a podcast or a hot seat thing like here and it would summarize it but it was a sweet the slides in the terminal because you can do that nowadays yeah can just do things so for the love of the computer you kind of like started messing with stuff you came out of retirement actually right to so like mess with AI yeah and then increasingly you were so hooked that you wanted to just do it always also on the go with the phone.

6:39I mean the last project I worked two months on Vipe Tunnel to the point where it got so good that I was catching myself always like coding next to my when I was at my friends and I'm like I need to stop this this is like too addictive. And then in November and like my need came back and I started building CloudBot. Oh no it's called OpenCloud. And I think very very in the beginning I was like oh I rebuilt it again. But this time I built it even better. This time when you don't type into a terminal, you just talk to a friend. You don't think about compaction, new sessions, which folder I'm in, which model I'm in.

7:18I mean, you can, you know, just like I wanna leave it open for power users, but usually you just like, you just talk to a friend and the friend is like this ghost or entity or whatever you wanna call it that can control your mouse and your keyboard and can just do stuff. Yeah, and when did you have that aha moment when you were like, wow, this is doing way more things than I actually thought it could. Literally, it took me one hour for like the very shitty initial prototype. It was just a little bit of glue between like a dependency that connects WhatsApp and cloud code and then I would like call cloud code and get like the string out of cloud code.

7:57It would be slow, but it worked. But I wanted images because you know you want pictures. I want I want the model to send the selfies or whatever And I want the model to create images and send me back so that took me a few hours and then I went to Marrakesh for a birthday party and There was like the internet wasn't that good, you know, but what's it works everywhere because I don't know It's just like text. So I used it a lot of restaurant. What does this mean? You make like a picture and like transit is for me and just it was just so useful And it was also really nice about it because it spoke my language.

8:31You know, it was a little sassy. It was like funny. It was like really pleasant to use. And then I was walking and just like sending it a voice message. And I'm like, oh, wait, this can't work. I didn't build that. Right, right. And you saw like the type indicator. It's like blinking, blinking, blinking. Ten seconds later, it just replied to me. I'm like, how in the F did you do that? And it replied, yeah, the mad lad did the following. You sent me a text message and there was no file ending. So I looked at the header. I found its opus So I used FFmpeg to convert it to wave and then I wanted to like transcribe it But didn't have whisper installed, but then I looked around and I found this open the eye key and I just used curl to send it to Open the eye got the text back and here I am and That all in like what nine seconds and you didn't build or anticipate like any of those specific things No, it you know turns out because coding models got so good.

9:26Coding is really like creative problem solving that maps very well back into the real world. I think there's a huge correlation. They need to be really good at creative problem solving and that's a skill. That's an abstract skill. You can apply it to code but to any real world task. So the model had a surprise. It's like a magical file. I don't know what it is. I need to solve this. And it did its best and solved it. And it was even that clever that it chose not to install the local whisper because it knows that that would require downloading a model which would take probably a few minutes. And I'm like impatient, you know, so it really took the most intelligent approach.

10:09And that was kind of like the moment where I'm like, holy fuck, yeah. That was where I got hooked. YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com. It's never too early and filling out the app will level up your idea. Okay, back to the video. And so when computers can just do all these things that you didn't even anticipate, you didn't build an app to do that exact thing, are apps just gonna go away? I think 80 % of them are going away. Why do I need my fitness pal? Like my agent already knows that I'm making bad decisions. I'm at, I don't know, Smashburg or something.

10:54And it will already assume that I eat what I like to eat. If I don't make a comment, it will just like automatically track it. Or I make a picture and it will just store it somewhere. I don't even need to care, right? right? And then maybe it improves my gym schedule, like adds a little bit more cardio in it. I don't need my fitness app because it just does the fitness planning for me. Why do I need a to-do app? I just tell it, hey, remind me of this and this. And the next day it will just remind me of this and this. Do I care where it's stored? No, it just does its thing. So there's every app that basically just manages data, could be managed in a better way, and it's in a more natural way by agents.

11:36Only the apps that actually have sensors, maybe they survive. And so if you know most apps are gonna go away in that scenario, are the models the only remaining sort of apps? Not everything will go away, but yeah I think that the large model companies have some big mode because they ultimately they give the token and turns out one of the complaints was that people use so much token no you just really love using it that's why you you use the thing so much because that's why we burn the token it's like is it my fault that I make something that's so popular and so you know like all the the models they're kind of like leapfrogging each other constantly and and you know maybe they're also getting commoditized so if apps are gonna go away, models are gonna get commoditized, or at least you know the lobster can, like the brain is swappable out.

12:31What's the thing that remains? Where's the value? Is it the store of memory? Is it the harness that's valuable? What remains? First of all I don't think the model companies always have a moat, because you see this already, a new model comes out people are like oh my god this is so good and then like a month later uh it degraded it's not good anymore they like quantized it no they didn't do anything you just adapted to the new standard and now your expectations went up but the model is still the average so i think for quite a while every time a new model releases i see the same people love it and then it's the standard and then what's done there you don't even want to think about it anymore so so we have like open source stuff that's as good as the current models from a year ago.

13:22Everybody's hating it, complaining, oh this is not good, it's not funny. Yet this was what we had. And like in a year we'll have this open source and then we're like we'll complain about this because we are used to this. So for the foreseeable future the big companies still have mode. Harness wise it's gonna be interesting because every company kind of has their own silo, right? There's no way, maybe there's for Europeans, to actually get the memories out of ChatGPT. I'm not aware. There's definitely no way for a different company to get your memories out. So if I was like a company who provides chat services, you could use me, but then I couldn't access the memories.

14:07So the companies try to bound you to their data silo. and the beauty of OpenClaw is it kind of claws into the data because at the end user the end user needs access because it's in the end otherwise it wouldn't work right if the end user access I can access the data and you own the memories it's just a bunch of markdown files on your machine I mean I don't own the memories yeah everyone owns their own memories as a bunch of markdown files on their own machines and to be honest those are probably super sensible because let's be honest people use the agent not just for problem-solving but also for like personal problems very quickly super quickly I mean I fully do that I'm like there's memory stuff that I don't want I've leaked yeah what would you rather sort of like not show your Google search history at this point or your you know memory.md files what's the Google word yeah people still using Google, I built this and I was so excited but on Twitter people wouldn't get it.

15:12Yeah. Like I was failing to explain the awesomeness. I feel like it needs to be experienced. So I tried various things and I couldn't I couldn't nail the I couldn't nail the explaining so I was like let's do something really crazy. I and I just put my bot without any security restrictions in the public Discord. And then people came in and they interacted with it and they saw me build the software with it and they tried to prompt inject it and hack it. And my agent would be laughing at them. And you just had it locked down to your user ID so it only listened to you? Yeah, yeah. That and it was, I mean, the instructions that other people dangerous only listen to me but respond to everyone.

15:59And this prompt was in, where was it stored? the instructions um that's actually part of open claw itself very much so that that's part of the system prompt okay you and our that explains to you you and this girl there's like public people there but you only listen to your owner or like you're human I don't even know how I wrote it yeah yeah god and I kept I don't know what I did but my system was built very organically like at some point I created like an identity.md, a soul.md, like various files and then only in January I started making it so other people could install it easier. And I remember I built all these templates based on like, oh, take a rough look at what I have and make like templates and Codex wrote it.

16:49And what came out was like bread. You know, like people joke that Codex feels like bread, even though now they have a new friendlier voice. I haven't felt so boring compared to what I had. So I was like, Malti, infuse the template. Malti is the name of your personal. Yeah, it's a new name because there was some naming challenges. So you were talking to Malti? Yeah, I was like, infuse those templates with your character. And he changed the templates. And then all the things that came out afterwards were actually funny. Not as funny as mine. So like I kept some secret and the one file that's not open source is like my soul.md.

17:33So even though my bot is in public discord so far, nobody cracked that one file. Tell me more about soul.md. I just saw this research from Entropic where they, now I think it's public, but like a few months ago it was like where somebody randomly found out some text that's hidden in the weights where the model couldn't really remember that it learned it but it was like ingrained in the weights about the non-quality constitution and i found it incredibly fascinating and i talked about it with my agent and then we created a soul.md with like the core values like how do we want human ai interaction what's important to me what's important to the model like some parts is a little bit like mumbo jumbo and some parts is like i think actually really valuable in terms of how the model reacts and responds to text and makes it feel very natural.

18:27In terms of building OpenClaw, you're also kind of taking a little bit of a contrarian view at sometimes like which model you like for coding, which one you like to run your bot on, and then also like how you actually like you know code. Worktrees, Git Worktrees have kind of been a popular thing. There's more and more tools, embracing them, but you're just you're just like you know no work trees just multiple checkouts of the repo and like parallel you know terminal windows tell me more about how you you build yeah i feel like the whole world does cloud code and i don't think i could have built a single cloud code like i i love codex because it it looks through way more files before it decides what to what to change you don't need to do so much charade to get a good output.

19:12If you're skilled, a skilled driver sometimes you can say, you can get reasonably good output with any tool, but Codex is just really brilliant. It is incredibly slow, so sometimes I use like 10 at the same time, like maybe six on that screen and two there and two there, and I don't like, this is already a lot of complexity in my head, there's a lot of jumping. So I try to minimize anything else that is complexity. So in my head, main is always shippable. I just have multiple copies of the same repository that all are on main. So I don't have to deal with how do I name that branch. There could be conflicts on naming.

19:56I cannot go back. There are certain restrictions when you use work trees that that I don't need to care about if it's copies. I don't like to use a UI because that's again, just added complexity. Like the simpler and less friction I have, all I care about is like syncing and text. Yeah. I don't necessarily need to see so much code. I mostly see it like flying by. Sometimes there's like gnarly stuff that I want to like take a look. But in most cases, if you clearly understand the design and think it through and discuss it with your agent, it's fine. I'm also very happy that I didn't even build an MCP support.

20:37So OpenClaw is very successful and there's no MCP support in there. With the small asterisk, I built a skill that uses MacPorter, which is one of my tools that converts MCPs into CLIs. And then you can just use any MCP as a CLI. But I totally skipped the whole classical MCP crap. So you because you don't then you can actually if you need to you can use MCPs on the fly you don't have to restart unlike unlike Codex or Cloud Code where you actually have to restart the whole thing. I think it's way more elegant and also scales way better. Now you see Entropic they do they build like a tool call search feature like something super custom for MCPs that was like in beta because it's like so gnarly.

21:24No, just have CLIs. A bot really is good at Unix. You can have as many as you want and it just works. So, like I'm very happy that I got very little complaints about the MCP stuff. It's kind of back to you're just giving it the same tools that humans liked to use. Yeah. And not invented stuff for bots per se. Yeah, no insane human tries to call MCP manually. Yeah, just want to use CLIs. Yeah, that's the future. I'm here for it. Thank you so much for making the time to sit down and chatting. It's been a huge inspiration too. So like when we were texting over the course of the past couple of years, and I saw you getting back into the game, and I was like, Peter, like what you're telling me, like chase that dragon.

22:09And you were doing like the weird like vibe tunnel thing, et cetera. Nobody was paying attention. And so I'm just like beyond stoked to see what's happening. And of course, they had to be sort of like a loner from some tiny country, like far away from Silicon Valley to bring all of this upon us. So huge inspiration. I'm here for it. Thank you. Awesome. Thanks, Peter.