Pod Insights Y Combinator Podcast OpenClaw And The Future Of Personal AI Agents About this episode 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 0:00 Speaker 00 Today, 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.
0:38 Speaker 00 So good to see you, man.
0:39 Speaker 01 Hey, what's up?
0:41 Speaker 00 So, you've made something people want.
0:44 Speaker 01 It seems so.
0:45 Speaker 00 Yeah. OpenClaw, as it's called now, has absolutely...
0:48 Speaker 01 Name number five, yeah.
0:50 Speaker 00 Has been absolutely exploding, the internet. How have the past one or two weeks been for you, man?
0:56 Speaker 01 Oh, my god. I need like, I need a cave. A week of solitude.
1:03 Speaker 00 You came out of the cave and you want to go back to the cave like a lobster.
1:07 Speaker 01 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.
1:21 Speaker 01 But clearly, I hit something that spurred up emotions and made people interested and inspired people. It's really cool.
1:28 Speaker 00 And a lot of people have been working on, you know, AI and even personal assistants. Like, what is it that made OpenClaw take off?
1:36 Speaker 01 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 way more powerful.
1:53 Speaker 00 Yeah. The machine can do anything that you can do with the machine.
1:56 Speaker 01 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. ChatGPT can't do that.
2:07 Speaker 00 You gave it all the skills that you have yourself.
2:10 Speaker 01 A friend told me, like, he installed OpenClaw and it... And then it asked it, "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?"
2:26 Speaker 01 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. It's also, you also give it all the data, right? So it can surprise you in many ways.
2:52 Speaker 00 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 I R L. Like, what's happening?
3:12 Speaker 01 I think that's the natural next step. Like, okay, I'm gonna book a restaurant. My bot will reach out to the restaurant bot and do a negotiation.
3:23 Speaker 01 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 then a human then calls the restaurant because they don't like bots.
3:35 Speaker 00 Or walks there, just stand in line.
3:37 Speaker 01 If he doesn't get a robot.
3:38 Speaker 00 For the owner of the bot.
3:41 Speaker 01 And I imagine if 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, my work stuff. Maybe one is our relationship bot that cares like everything in between. 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. But I feel we are, we are on the timeline now.
4:07 Speaker 00 It seems like everyone was chasing sort of like the, sort of like centralized god intelligence. And it was sort of emerged over the past, you know, 10 days or so. It's sort of like the swarm intelligence and, and the community intelligence.
4:20 Speaker 01 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? I think one human being would probably just like, not even be able to like find food.
4:37 Speaker 01 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 really have like.
4:52 Speaker 01 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 gonna be very exciting.
5:03 Speaker 00 Yeah, you kind of like opened a window into the future and now a ton of people are kind of like building, building on it. And have sort of like their aha moment. Can you walk me back to when you had your aha moment and can like recount that very moment?
5:16 Speaker 01 I wanted something like just type stuff so 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.
5:31 Speaker 01 And then I built a whole bunch of other stuff. And kind of like build up my army. And then in November.
5:40 Speaker 01 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 would still do stuff. Or being finished.
5:49 Speaker 00 And doing stuff was coding, you were coding stuff.
5:51 Speaker 01 Yeah, of course.
5:52 Speaker 00 Were you coding something else or were you coding the thing itself?
5:57 Speaker 01 No, no, that was just like the need was again there and I'm like.
6:01 Speaker 00 What were you coding at the time? What were you building?
6:04 Speaker 01 My God, my GitHub is like, it's like forty 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 show of the slides in the terminal. Cause you can do that nowadays.
6:24 Speaker 00 Yeah.
6:24 Speaker 01 You can just do things.
6:25 Speaker 00 So for the love of the computer, you kind of like started messing with stuff. You came out of retirement actually, right? To sort of like mess with AI.
6:34 Speaker 01 Yeah.
6:34 Speaker 00 And then increasingly you were so hooked that you wanted to just do it always also on the go with the phone.
6:39 Speaker 01 I mean, the last project, I, I worked two months on Vibe 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, like my need came back and I. I started building Cloudbot. 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 a friend. You don't think about compaction, new sessions, which folder I'm in, which model I'm in. I mean, you can, you know, it's just like, I wanna leave it open for power users.
7:23 Speaker 01 But usually you're 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.
7:34 Speaker 00 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.
7:41 Speaker 01 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 Claude code. And then I would like call Claude code and get like the string out of Claude code. It would be slow, but it worked. But I wanted images, because you know, you want pictures. I want, I want the model to send selfies or whatever, and I want the model to create images and send me back. So that took me a lot of hours. And then I, I went to Marrakech 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 text. So I used it a lot, oh, restaurant, what does this mean?
8:24 Speaker 01 You make like a picture and like translate this for me and just, it was just so useful. And it was also really nice about it because it, it spoke my language, you 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.
8:41 Speaker 01 And I'm like, oh wait, this can't work, I didn't build that.
8:43 Speaker 00 Right, right.
8:44 Speaker 01 And it's like the type indicator, it's like blinking, blinking, blinking. 10 seconds later, it just replied to me. And I'm like, how in the F did you do that? And it replied, yeah, the model did the following. You sent me a text message and there was no file ending, so I looked at the header, I found it's OPUS. So I used FFmpeg to convert it to WAV. And then I wanted to like transcribe it, but didn't have Whisper installed. But then I looked around and I found this OpenAI key and I just used curl to send it to OpenAI. Got the text back and here I am. And then that all in like, what, nine seconds?
9:17 Speaker 00 And you didn't build or anticipate like any of those specific things?
9:21 Speaker 01 No, it, you know, turns out, 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 huge correlation.
9:36 Speaker 01 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 like to any real world task. So the, the model had a, oh 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, 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, it really took the most intelligent approach. And that was kind of like the moment where I'm like, holy fuck. Yeah. Uh, that was where I got hooked.
10:18 Speaker 02 YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com/apply. It's never too early and filling out the app will level up your idea. Okay, back to the video.
10:32 Speaker 00 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?
10:41 Speaker 01 Uh, I think 80% of them are going away. Why do I need MyFitnessPal? Like my agent already knows that I'm making bad decisions. I'm at, I don't know, uh, smash burger or 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? And then my, maybe it, it improves my, my gym schedule. Like adds 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. 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.
11:25 Speaker 01 So there's a, every app that basically just manages data could be managed in a better way and it's in a more, in a more natural way by agents.
11:36 Speaker 00 Yeah.
11:36 Speaker 01 Only the apps that actually have sensors, maybe they survive.
11:40 Speaker 00 And so if, you know, most apps are gonna go away in that scenario, are the models the only remaining sort of apps?
11:48 Speaker 01 Not everything will go away.
11:51 Speaker 01 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 use this thing so much, because that's why you burn the token.
12:11 Speaker 01 It's like, is it my fault that I make something that's so popular?
12:14 Speaker 00 And so, you know, like all 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. What's the thing that remains? What's, where's the value? Is it the store of memory? Is it the harness that's valuable? What is, what remains?
12:42 Speaker 01 First of all, I don't think the, the model companies always have a mode. And 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, 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 hear the saying, people love it. And then it's the standard. And then what's down there, you don't even want to think about it anymore. 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, it's not funny. Yet this was what we had.
13:26 Speaker 01 And like in a year, we'll have this open source. And then we'll 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, their own silo, right? You, you, there's no way, maybe there is for Europeans, to actually get the memories out of ChatGPT. I don't, I'm not aware. There's no, there's, definitely there's no way for a different company to get your memories out. So if, if I was like a company who like provides chat services.
14:04 Speaker 01 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 datas. Because 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.
14:23 Speaker 00 And you own the memories? It's just a bunch of markdown files on your machine?
14:27 Speaker 01 I mean, I don't own the memories.
14:28 Speaker 00 I mean, you, yeah, everyone owns their own memories. As a bunch of markdown files on their own machines.
14:34 Speaker 01 And to be honest, those are probably super sensible. Because, let's be honest, people use their agent not just for problem solving, but also for like personal problems.
14:46 Speaker 00 Very quickly, super quickly.
14:48 Speaker 01 I mean, I fully do that. I'm like, there's memory stuff that I don't want to have leaked.
14:53 Speaker 00 Yeah, what would you rather sort of like not show? Your Google search history at this point? Or your, you know, memory dot M D files?
15:00 Speaker 01 What's the Google word? People still using Google? I built this and I was so excited. But on Twitter, people wouldn't get it.
15:12 Speaker 00 Yeah.
15:12 Speaker 01 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 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.
15:47 Speaker 00 And you just had it locked down to your user ID? So it only listened to you?
15:50 Speaker 01 Yeah, yeah. That, and it was, I mean, the instructions that other people dangerous. Only, only listen to me, but respond to everyone.
15:59 Speaker 00 And this prompt was in, where was this stored? The instructions?
16:03 Speaker 01 Um, that's actually part of OpenClaw itself. Very much so, that's part of the system prompt. Okay, you and I, that explains to you, you in Discord, there's like public people there. But you only listen to your owner. Or like your human, I don't even know how I wrote it.
16:17 Speaker 00 Yeah, yeah.
16:18 Speaker 01 Your god. And I kept, I don't know what I did, but.
16:27 Speaker 01 My system was built very organically. Like at some point I created like an identity dot M D, soul dot M D, 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. 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 it yet. But the new bots, they felt so boring compared to what I had. So I was like, Multi, infuse the templates.
17:05 Speaker 00 Multi is the name of your personal.
17:07 Speaker 01 Yeah, it's a new name because there were some naming challenges.
17:13 Speaker 00 So you were talking to Multi?
17:15 Speaker 01 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 dot M D. So even though my, my bot is in public Discord, so far, nobody cracked that one file.
17:39 Speaker 00 Tell me more about soul dot M D.
17:41 Speaker 01 I just saw this research from Anthropic about 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, now they call it the constitution. And I found it incredibly fascinating. And I talked about it with my agent and then we created a soul that I leave is like the core values, like how do we want human AI interaction? What's important to me? What's important to the model?
18:17 Speaker 01 Some parts is a little bit like mammut 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.
18:27 Speaker 00 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. 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 worktrees, just multiple checkouts of the repo and like parallel, you know, terminal windows. Tell me more about how you you build.
18:54 Speaker 01 Yeah, I feel like the whole world does cloud code. And I don't think I could have built this thing with cloud code. Like, I love Codex because 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. If you're skilled, a skilled driver or something, you can say, you can get reasonably good output with any tool. But Codex is just, is just really brilliant. It is incredibly slow. So sometimes I use like 10 at the same side, 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.
19:37 Speaker 01 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?
19:54 Speaker 01 There could be like conflicts on naming, I cannot go back. There are certain restrictions when you use worktrees 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.
20:09 Speaker 00 Yeah.
20:09 Speaker 01 Like, the simpler and less friction I have, all I care about is like syncing and text.
20:16 Speaker 00 Yeah.
20:16 Speaker 01 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, 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 a small asterisk, I built a skill that uses McPorter, 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 because you don't then you can actually,
21:01 Speaker 01 if you need to, you can use MCPs on the fly. You don't have to restart, unlike unlike Colix 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 in Tropic, they do, they built like a tool called Search Feature, like something super custom for MCPs. That was like in beta because it's like so gnarly. Now just have CLIs, but really is good at Unix. You can have as many as you want and just works. So like I'm very happy that. I guess I got very little complaints about the MCP stuff.
21:36 Speaker 00 It's kind of back to you're just giving it the same tools that humans liked to use.
21:43 Speaker 01 Yeah, yeah.
21:44 Speaker 00 And not invented stuff for for bots per se.
21:46 Speaker 01 Yeah, humans, no insane human tries to call MCP manually.
21:51 Speaker 00 Yeah, just want to use CLIs.
21:52 Speaker 01 Yeah, that's the future.
21:54 Speaker 00 I'm here for it. Thank you so much for making the time to sit down chatting. It's been a huge inspiration to. 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. And nobody was paying attention. And so I'm just like beyond, you know, stoked to see, you know, what's happening. And and of course, it had to be sort of like a loner from some like tiny country, like far away from Silicon Valley. Just like, you know, bring all of this upon us. So a huge inspiration.
22:26 Speaker 01 I'm here for it. Thank you.
22:27 Speaker 00 Awesome. Thanks, Peter.
Previous We're All Addicted To Claude Code Next The New Way To Build A Startup Page updated October 12, 2026 · transcript and summary are machine-generated