OpenClaw And The Future Of Personal AI Agents - podcast episode cover

OpenClaw And The Future Of Personal AI Agents

Feb 07, 202623 min
--:--
--:--
Download Metacast podcast app
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more

Summary

Creator Peter Steinberger details the journey of OpenClaw, a local-first, open-source AI agent that's gone viral for its task execution capabilities and deep integration with personal devices. He explores how such agents could make many current apps obsolete, emphasizing the critical importance of individual data ownership and privacy. Steinberger also shares his unique development philosophies, including how he instilled personality into his agent and his belief in "swarm intelligence" for AI's future.

Episode description

You’ve probably already heard all about OpenClaw (formerly Clawdbot/Moltbot). The viral sensation is an open-source AI assistant that runs on your own device, connects with messaging apps you already use, and goes beyond chat to actually execute tasks like managing your email, calendars, files, workflows, and more. Now meet the man behind it. YC’s Raphael Schaad sat down with Peter Steinberger, the creator of OpenClaw, to discuss the “aha” moment behind the viral personal AI agent, why local-first agents could replace many of today’s apps, and how personal agents will reshape the future of software.

Chapters:

00:00 – OpenClaw takes over the internet

00:44 – Life after going viral

01:28 – Why OpenClaw took off, what sets it apart

02:56 – Bots talking to bots (and hiring humans)

04:11 – From “God AI” to swarm intelligence

05:07 – Peter’s original “aha” moment

06:38 – Rebuilding the agent as a conversation

07:38 – The moment it exceeded expectations

10:21 – Are apps going to disappear?

12:31 – Memory, data silos, and ownership

14:39 – The privacy reality of personal agents

15:05 – Letting the bot loose in public Discord

16:55 – Giving an agent a personality

18:19 – Contrarian building philosophy

20:09 – CLIs vs MCPs

21:28 – Building for humans first

21:46 – The road ahead

Apply to Y Combinator: https://www.ycombinator.com/apply

Work at a startup: https://www.ycombinator.com/jobs


Transcript

OpenClaw takes over the internet

Today I'm sitting down with Peter Steinberger, the creator of OpenClaw, the open source personal AI agent that has completely taken over the The GitHub repo exploded to over 160,000 stars practically overnight. The community has built countless projects like Multbook, 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. So good to see you man. Hey, what's up? Um so you've made something people want.

Life after going viral

It seems so. Yeah. Uh OpenClaw as it's called now has absolutely Name number five, yeah. Has been absolutely exploding the internet. Um 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 you came out of the cave and you wanna go back to the cave like uh like the lobster. 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. Uh I got some incredibly cool stuff. I got some incredibly bad stuff. Um but clearly I hit something that Spur up emotions and make people interested and inspired people and it's really cool. And a lot of people have been working on, you know, AI and even personal assistance. Like what what is it that may open claw take?

Why OpenClaw took off, what sets it apart

I think my big difference is that it actually runs on your computer. Like every s 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 way more powerful. Yeah. 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, my bed, it can control the temperature of my bed. Uh ChatGPT can't do that. You gave it all the skills that you have yourself. A friend told me like he installed OpenClaw. And it and then it asked it 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 OpenClough

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, y it it can surprise you. 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 and 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.

Bots talking to bots (and hiring humans)

What's happening? I think that's a natural next step. Like, okay, I wanna book a restaurant, my bot will reach out to the restaurant bot and do the negotiation. Like Because it's more efficient. Or or maybe it's like an old restaurant so my bot needs to actually get some some human work done so that the new man then calls the restaurant because they don't like bots.

Or or walks there to stand in line. If he doesn't get a robot for the owner of the bot. And now imagine that like maybe if I if I have even multiple bots. Like maybe I have like specialists. One is like for my private life and one is for like my person my my my work stuff. Maybe one is our relationship bot that gets like everything's in between. Uh I don't know. We're so early. There's still so much. So many things that we haven't really figured out if it actually works.

I feel we are we are on the timeline It seems like everyone was chasing sort of like the sort of like centralized god intelligence and what has sort of emerged over the past, you know, ten days or so is sort of like the swarm intelligence um and and the community intelligence. I think that if you look at One human being.

From "God AI" to swarm intelligence

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? I think one simul being would probably just like not even be able to like find food. Um but as a group, we specialize. As a larger society we specialize even more. So what can we learn from that that we can apply to AI? You know, we we already have like

AI that specializes in certain things. Um even though it's it's generalized intelligence, what if it actually is also specialized? So I know it's gonna be very exciting. Yeah, you kinda like opened a window into the future and now a ton of people are kinda like building building on it and have sort of like their aha moment. Um can you walk me back to when you had your aha moment and can like re recount that very moment?

Peter's original "aha" moment

I wanted something to like just type stuff so that my computer would do stuff. Like very simple. And then I built I built a version of that in May June that was cool but wasn't really it. Um And then I build a whole bunch of other stuff and kind of like build up my army. And then in November. That was a day where I wanted this again. I went to the kitchen and all I wanted was check up if my computer was still do stuff. Always being fit.

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 it again there? And I'm like. What were you coding at the time? What were you building? My god. It's like 40 projects. I don't even know. I think it was summarized. It's like a it's like a little C L I app where you can give it a little bit of a little bit of a little

Whatever like a podcast or um a hot seat thing like here and it would summarise it. But it will also show you the slides in the terminal. Because you can do that nowadays. Yeah. You can just do things. So for the love of the computer you kinda like started messing with stuff.

Um you came out of retirement actually, right? Um to sort of 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. I mean the last project I I worked two months on Vipe Tunnel.

Rebuilding the agent as a conversation

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 was like, I need to stop this. This is like too addictive. And then in November, my need came back and I started building CloudPot. Oh, now it's called Open Cloud. 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 you talk to

You don't think about compaction, new sessions, which folder I'm in, which model I'm in. I mean you can, you know, just like I wanna leave that open for power users, but usually you just like you just talk to a friend and the friend is like Ghost or entity or whatever you want to call it.

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, well this is doing way more things than I actually thought it could. Literally I it took me one hour.

The moment it exceeded expectations

for like the the very shitty initial prototype. It was just a little bit of glue between like a dependency that connects WhatsApp and clot code. And then I would like call cloud code and get like the string out of clot code. It would be slow, but it it wouldn't. But I wanted images.'Cause uh you know you want pictures. I want I want I want the model to send some selfies or whatever and I want the model to create images and send me back. So that took me another few hours.

And then I I went to Marrakesh. for a birthday party and there was like the internet wasn't that good you know whatsapp works everywhere because i don't know it's just like So I used it a lot, I love restaurant, what does this mean? You make like a picture and like transcend this for me and just

It was just so useful. And it was also really nice about it because it it it spoke my language. You know, it's it 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 and you saw like the type indicator, it's like blinking, blinking, blinking. Ten seconds later, just reply to me. I'm like, how in the F did you do that?

And it replied, yeah, the Mad Light 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 FFmpack to convert it to Wave. And then I wanted to like transcribe it but didn't have VISP installed. But then I looked around and I found this OpenEI key and I just used curl to send it to OpenEI. Got the text back and here I am.

And um 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, um, because coding models got so good. Coding is really like creative problem solving that maps very well back into the real world. I think I think there's there's a 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 to code, but like to any real world task. So the the model had a I was surprised, there's like a magical file, I don't know what it is, I need to solve this. And he did its best and solved it. And it was even that clever that it

It chose not to install the local Visper because it knows that that would require downloading a model, which would take probably a few minutes. And I'm like impatient. uh intelligent approach. And that was kind of like the moment where I'm like, holy Uh that was where I got hooked. YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com slash apply. It's never too early and filling out the app will level up your idea. Okay, back to the video.

Are apps going to disappear?

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? Uh I think eighty percent 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 uh Smash Burger something and 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'll just store it somewhere. I don't even need to care, right, right? And then my maybe it it improves my My gym schedule like has a little bit more cardio in it. I don't need my my fitness app because it just it just does the fitness planning for me.

Uh why do I need a to-do app? I just tell it, hey, remind me of this and this. And then 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 a every app that basically just manages Data could be managed in a better way, in a s in a more in a more natural way by agents. Yeah. Only the apps that actually have sensors, maybe this okay.

And so if, you know, m most apps are gonna go away in that scenario, um are the models the only remaining sort of apps? Not everything will go away. But yeah, I think the the the large model companies have some big Cause they ultimately they give the token. And turns out

Well one of the complaints was that people use so much token. No, you just really love using it. That's why you you use this thing so much because that's how you burn the token. Um 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 kinda like leapfrogging each other constantly and And you know, maybe they are also getting commoditized. So if apps are gonna go away, models are gonna get commoditized, or at least

uh you know the lobster can like the brain is is is swappable out. What's the thing that remains? What where's the value? Is it the store of memory? Is it um the hardness that's valuable? What what is w what remains?

Memory, data silos, and ownership

First of all, I don't think The model companies always have a mode. 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 quanticized 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 f 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. So so we have like open source stuff that's as good as the current models from a year ago. Everybody's hating it, complaining, oh this is not good, this is not funny. Yet this was what we had. And like in a year we'll have this open source. And then everybody like we'll complain about this because we are used to this.

So uh for the the foreseeable future, the big companies still have mode. Harness-wise, it's gonna be interesting because Every company kinda has their own their own silo, right? You you there's no way maybe there is for Europeans to actually get the memories out of Chat GPT. Mm. I'm I don't I'm not aware. There's no there's uh definitely there's no way for a different company to get your memories out. So if if if I was like a company who like provides chat services,

You could use me but then I couldn't access the memories. So like the companies try to like 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 it's in the end otherwise it wouldn't work, right? If the end user had access, I can access the data.

And you own the memories. It's just a bunch of markdown files on on your machine. I mean I don't own the memories of other people. Yeah, everyone owns their own memories as a bunch of markdown files on their own machine. And to be honest, those are probably super sensible because

The privacy reality of personal agents

Let's be honest. Um People use their agent not just for problem solving but also for like personal problems. Very quickly. Super quickly. I mean I I I I fully do that. I'm like there's memory stuff that I don't want to have leaked. Yeah, what would you rather um uh sort of like not show? Your Google search history at this point or your you know memory.md files? What's what's the Google word? Yeah yeah.

I built this and I was so excited but on Twitter people wouldn't get it. Yeah. Like I I was failing to explain the awesomeness. I feel like

Letting the bot loose in public Discord

It needs to be experienced. So I s I tried various things and I I 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 just created a Discord 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 they don't want to listen to you? Yeah, yeah. That and it was I mean virtually the instructions that other people dangerous only only listen to me but respond to everyone. And this prompt was in where was it stored, the instructions? Um

That's actually part of OpenClaw itself. Very much so the the that's part of the system prompt. Okay, you and now that explains to you, you're in Discord, there's like public people there, but you only listen to your owner. Like you're human. I don't even know how I wrote it. Yeah, yeah, yeah. You're 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 like various files, and then only in 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. And what came out was like,

Brad. You know like people joke that codex feels like Brad, even though now they have a new friendlier voice. I haven't tried that yet.

Giving an agent a personality

But the new bots they felt so boring compared to what I had. So I was like Multi. Infuse the temptation. Multi is the name of your personal. Yeah, that's a n it's a new name because Yeah yeah uh there was some naming challenges. Yeah so so you were you were t talking to multi? Yeah. I was like infuse infuse those templates with your your character. And he changed the templates. And then and then like All the things that came out afterwards were like 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. So

Even though my my bot is in public Discord so far nobody cracked that one file. Tell me more about Sol.md. I just saw this research from Anthropic about where the 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 a now they call it a constitution.

And I found it incredibly fascinating. So and I 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 mambu jumbo and some parts is like I think actually really valuable in terms of how the model reacts.

Contrarian building philosophy

and responds to text and makes it feel very natural. In terms of building OpenClaw, you're also kind of taking a little bit of a contrarian view at some times. 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. Um work trees, Git work trees 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 Like I I love Codex because it it looks through way more files before before it decides what to what to change. You don't need to do so much charade to get a good output. If you're skilled a skilled driver I sometimes even say.

Uh you can get reasonably good output with any tool. But codex is just It's just really brilliant. It is incredibly slow. So sometimes I use like ten at the same side at the same time. Uh like maybe six on that screen and uh 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 f 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 are all our o main. So I don't have to deal with how do I name that branch? Um there could be like conflicts on naming. I cannot go back. It it's there are certain restrictions when you use work trees 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. Yeah. Like

CLIs vs MCPs

They're 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 I mostly see it like flying by. Sometimes there's like gnarly stuff that I wanna like take a look. But in most cases, if you clearly understand the design and think it through and discuss it with your with your agent, it's fine. I'm also very happy that

I didn't even build an MCP support. So 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. Um 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 built like a tool call search feature, like something super custom for MCPs that was like in beta because it's like so gnarly.

No, just have CLIs. Bot really is good at Unix. You can have as many as you want, and it just works. So I'm very happy that.

Building for humans first

I just I got very little complaints about the MCP stuff. It's kind of back to you're just y giving it the same tools that humans liked to use. Yeah. Yeah. And not invented stuff for for for bots per se. Yeah.

The road ahead

No insane human tries to call M C P manually. Yeah, it's gonna use C L I's. Yeah. I'm here for it. Thank you so much for making the time uh to sitting down chatting. It's been a huge inspiration too. So like when we were texting, you know, 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. And you were doing like the weird like vibe tunnel thing, et cetera. Nobody was t paying attention. And so I'm just like beyond, you know, stoked to see, you know, what's happening. And um and of course they had to be sort like a loner from some like tiny country like far away from Silicon Valley to like you know, bring all of this upon us. Um so huge inspiration. I'm here for it. Thank you. Awesome. Thanks.

This transcript was generated by Metacast using AI and may contain inaccuracies. Learn more about transcripts.
For the best experience, listen in Metacast app for iOS or Android