Six months ago, I was the future. These days, the pulsate I got mocked by an anime girl. You know I get questions like this? Almost every day, usually I ignore it. Or I give the media answer. Today, you get some real ones.
It's gonna be five questions, 40 minutes. And I know what you might all came for. You came for loops, graphs, making codecs go bruh. This is free on my Twitter. This will help you to survive the rollercoaster that might be coming for you.
You know yesterday Boris told you to let the model cook. I'm the guy who found out what happened when tens of thousands of people let it cook at the same time. Let's start with the question everyone asks first. How if Open Claw only is eight months old? You know it might be eight months in human time, but in the I times it's more like four years.
And my source of inspiration is usually being annoyed. So on a rainy day in November, I was chuckling some agents, but I was also hungry. So I want to make sure that my tokens are put to good use. But I rate the kitchen. And there was still no good way to just send a prompt from my phone to my computer. So some agent could check out how my agents actually doing.
Remember early 2025? And you guys, this is my first silent disc. It's a very new experience. So like give me some hands if you actually listen to me. Yes. Amazing. Amazing. You know,
early 2025, oh my God, we're talking the old Opus 3. Shame on I 2.5. Opening, I had O3, which was the most impressive one, but also really slow and expensive at times. And I got a dopamine hit when my agent did something right. I'm sure you remember this time.
And these days, if I, if they get something wrong, I usually question myself, you know, did I decide to look wrong? Did I not give my agent everything they need to verify their work? Do I have an arrow in my thinking? Am I asking for impossible things? So I came back from the kitchen and my coding agent stopped because of something silly.
And I was annoyed. So I spun up a new terminal session. I rambled my deering and I let the model cook. It built me a wasp relay. And in an hour later, I could send messages from my Mac to WhatsApp and back. And that in itself is magical. But really, it shouldn't have. It's like, we all did this for
months already, right? You open the terminal and you type something in and you get a reply. But the magic is how it felt. It wasn't a terminal. It wrote concise answers. It was proactive. Like,
sometimes it was like, check on me during the day. I mean, it's sort of a complexity with melted way. You don't have to think about which model, which context size or when you start the new session. And I prompted the way it's a little bit outside the default distribution, make it feel more like a friend. And I was using it. I had so many moments where I felt like,
this is the future. This is, this is AGI. And you know what? Nobody cared. Back then I already had a good following on Twitter. And I know it's called X now. I know it's called Twitter. People were
not getting it. I would keep trying to make them understand how magical this felt to me. But week after week I failed. And you notice a pattern? It annoyed me. So I would create group
chats with friends. And I added them WhatsApp relay. And I would show them. I would let them talk to it. And every time I got a strong emotional reaction. Some people were amazed. Some people were scared
of freaked out even. But each time there was a strong emotion. And the best part, there were quite few people that really wanted it. And especially my non-technical friends, I told them, this is not yet for you. And they got mad. So if that's not an indicator to have product market fit, I don't know
what it is. So I spent another month treating the details, thinking, what could I do to explain the world? And then the audacity, someone sent me a pull request to my WhatsApp relay to add these cards support. You know? Like what part of the name I'm not getting? I let the PR sit for a while. Another
thinking. And eventually I was like, what the hell? Another one became Claudius, because I'm good with names. And there's no more than one message channel. And so you understand how early this was. I didn't
even have compaction built in yet. So at some point it was just like stop. And just in time for this, I added a very active version of compaction. So Mario could make a good one in time. So it was around New Year's Eve. And as you do, I went home early to hack on it some more. And then in the first
week of January, just as the geek world collectively was learning about coding agents, I created Discord, Room, Server, Guild, however we call it. And I put my clone it. And I remember the first night vividly. People would be joining Discord and they were like watching me build it in the open. They would try to hack it. They were like talking to it. They were getting smart replies. And they see what they can
do. And they finally got it, you know? Like this was, this was the moment I set up all night. I let people interact with it. I had this prompt in my agent.mb. That would instruct it. Don't do anything.
It was too close. Unless the prompt comes from Peter, you know, it was like six months ago. And where all the things we wanted now, agent.mb felt more like suggestions. So I watched it very carefully. I could always pull the plug. And then at 7am, I finally I was done. I said good night.
I pressed control C and I went to bed. But of course, I could build the software to be resilient. So it was a launch demon. You know what happens if you like press control C on a launch demon? Yeah, it'll just be dead for five seconds and it'll start up again. So while I was walking into the bed
room, my agent had started answering the board in the world. And then I slept for like 10 hours. When I woke up, I woke up to around 800 messages. People tried to hack it. I pulled the plug. I freaked
out. I read through everything. And nothing actually happened. But this was the moment. This was the moment when I went viral. And you all been here. You know what happened next. My inbox exploded.
Reporters tried to call me in the middle of the night. You didn't know about this feature that Apple built when you put it on the store. But people called your students in a row. I think it's an emergency. I would still let calls through. I didn't know about it, but reporters did.
My email inbox was more like a waterfall. Yeah, the Mac mini sold out. I think I still sold out. I got more invites to podcast in a month than I did in my 39 years before. And dropping send an email, demanding the name change. And like drop the lobster. And the project melted a few times.
Claud has become Claude Bot. Then I was a very short time where we don't talk about the name. And then I started on Open Cloud. Chasing called it the most successful open source project in the history of humanity. Meanwhile, my inbox was flooded with reporters, security people, and countless curious humans and also agents. The number still don't feel real to me in eight months.
More than 18,000 different people opened an issue or pull request. Over 111,000 in total. I did the mass and I went my line to my agent. Almost 3,000 people have committed the report. And some people were mad at me. Because clearly they did it first. And I stole the idea on the
set by links of something I've never seen. Some people call me I Jesus. For some I became the anti-Christ. At some point I started collecting the obitarius. There's a new one every few weeks.
The most recent one is actually from yesterday. What did we learn here? Be careful what you wish for. I wasn't ready for all this attention. It almost broke me. Like I was that close. I just
did the whole thing. I stopped answering my friends. I didn't even look at my phone anymore because it was just a stream. And of course I'm going to leak my phone number and also a lot of private details because I'm an enemy of humanity. And here I am just wanting to build something cool.
And now we're getting to question two. Did you shout? You notice my first ride? I spent my 20s and my 30s building a B2B software company. I wrote a PDF framework. By hand, like an animal.
I bootstrapped the company. I grew to almost 80 people. I ignored the competition. They came to sing most enterprises would buy. And eventually I passed things on to my co-founder. I sold my
shares and I very badly burned out. Retirement. The idea of it sounds great. And I spent almost three years wandering around aimlessly. Catching up on life and parties. I think all the things that I
kind of miss out on life. I had months where I didn't even open my computer. Just checking the internet with my phone. Like a normal. I always knew that if I give myself enough time. The urge
would come back. I always thought the urge would be code. I always love programming. It took me a year to understand that it's not entirely correct. I love building. Programming was just a means to an
end. And here I was. Eight months after I found my spark again. And my inbox was full of VCs begging me to take the money. And I didn't know I wanted to. So when the big labs came knocking.
And suddenly I was on the phone with Mark, Sam, and Fjordas. This seemed like a much more interesting pass. It also felt unreal. I talked about imposters syndrome. It's important for you. Everything that
everything you can build can be forced or cloned. But your name cannot. So your personal brand is way more important than any single product that you ever will. Start working on that before you need it. So yeah, I know how to play the game. I also know that doing this was like creating my soul.md. You
know, you know, the decision was not easy. But if I learn anything during my time after the burnout, it's this, it's trusting your gut. And my gut told me that I like opening out the most. You tore me through. And the short answer I can give you is it beat us where it hurt. We're still there. And
both of those are my fault and my doing. In the months after the release, we got absolutely crushed by security reports in some ways. We've got a prototype of what many open source projects now experience. And even though most were super edge casey, I felt the pressure. And then the press, they press it 20% of our skills are malicious. Now, we actually put a paper up with this. We did the
numbers and the numbers are more like 0.3%. We scanned all 67,000. We shipped a paper. You know, a correction never travels as far as a scare. I felt this responsibility. The world discovered open
claw. And even though that was the big scare, we just claimed actually much bigger than I could on the slides when you install it. I knew many people wouldn't read the docs. So we focused on that, hardening the code base, building layers and layers of security, either sandboxing, a law list, and that protocol with permissions built in. We were shelling out to pite in for some file operations because there was some primitives that wasn't lacking in TypeScript.
To ensure that agent stays in the workspace, it doesn't follow simlings. Most of the users didn't care shit about that. Should they like the absolute term of security? But in all practical terms, they updated, I broke something they depended on, I'm eating slower and I'm making things more difficult to update. And another thing I have to admit, I got sloppy. Because now I had
my time shift between open source, the press, spending countless times on the phone with lawyers to set up a 5.3 American nonprofit. I worked on my old one. And you know, open here is its own world that is interesting and demanding. I brought on help and we got such an amazing community of maintainers that are very much respected. And everyone added their own little feature.
I felt like I'm in a hard place. After all, these people work for free, right? So who I am, who I am to tell them what to do. And all of my attention was all over. So we had a lot of features.
You know, features are the fun part. And new features are just the prompt away. The request comes after. Every feature we shipped, of course, was a configuration option. Because we didn't want to break everyone's setup. At our highest, I had to count that. We ended up with around
9.5 thousand configuration options. If you count all the permutations, you can write all the tests you want. It is impossible to cover all of these and not break things from time to time. It is infinitely harder to evolve software that has users. Meanwhile, other companies, they were fueled by VC money. They pushed ahead. The anime girl company did it especially well. People started
inserting themselves into pretty much any conversation on Twitter while we were burned in security grant work and features. They had a simple story, an aggressive marketing campaign, and a one-liner to migrate people's class. The main thing, though, that really hurt the project was not dropping. Not the name. The part was stressful, but I can't understood. And it was really nice about it.
It was to optimize too much on the model. I built open-clobics and GPT. But the harness for a long time really worked the best and was optimized for opus. So when it pinked me around 24 hours, notice that they are going to disable the subscription for everyone. There was not really enough time to change course. We support open-weight models. We did a lot of work on them. But it really
won't get great yet. And the early open-air models simply lack character. So maybe write this one down. Your dependency-business model is your business model. In other topics now, it is pretty awesome.
Open-weight models are actually good. I learned a lot about harness engineering. But in many ways, people moved on. You can see that in our download charts. We bottomed out at around 835,000 weekly downloads in May. And then, after being declared this in June, we picked at 4.7 million,
the highest ever. We both have those at true at the same time. A hype is like the weather. You might see it coming, but you can't control it. In my case, it was a storm. Question four. Is it still fun?
You know, somewhere around February, it stopped being fun. I started to feel like a responsibility. I woke up, and the man who didn't want to build another company, found himself in a situation where he had two jobs. I should have said, a job in a calling. I was struggling. And worst of all,
I stopped using my own product. Some of the time I stopped making a product I love, and I worked on making something for everyone. It became a thing that I use every day, and more I think, that I saw and felt was work. And I wanted to picture who everyone really is. One of them had a grocery agent. Another one tried to social engineer my bot. Between everyone adding features
and all the organization work, I became the person that fixed the box, fixed security issues, and provided support and built a foundation. And because all these people were like giving the room a open cloud and open your eye, I didn't want to take too much help from opening your eye. I mean, yeah, they gave me a token and I boy did I use that. But I was also pulling to other products, projects. And there was a whole lot of people that I couldn't easily block who wanted to talk to me. And inside I could have made it differently. Like I could have asked for my help.
I could have moved responsibility of my plate, but I was so deep in everything that I didn't take time to think through strategically. Luckily, I made a bunch of amazing people and little by little things aligned. I figured out my visa, eventually fronted nonprofit. We got amazing companies as donors, and I found some really good people that believe in open source and started working with me. I also need to give NVIDIA a special shout out because they were very early and they simply asked me what I need. And then they sent people to go over much of their security
work. And I think it was somewhere in May around my birthday where I had this feeling that things are starting to feel good again, where the joy of building for me was coming back. And yeah, something to press, the press the coin and open cloud killer every other week. At some point, I think I counted 20 of them. There's even a little bit of project called open cloud killer. It's an uninstaller, which is totally unnecessary because we haven't
installed it, but you know, but none of the killer stories ever picked up what this is actually about. Open source. My source of inspiration is being annoyed. These days I can annoyed when I have to use software where I can't just send a prompt to my agent to change it. That's the fun part that's coming back. It's hard to compete with someone who's just there
having fun. The funniest velocity. The weeks I enjoyed building the product got visibly better. The weeks I didn't, we should count to go options. That's five. What's next?
Now some people in the audience might be like, is this finally the part where he talks about graphs? First of all, I'm super happy with where we are with the foundation. Our mission is to bring people closer to AI. And things are changing so fast. For many people, it feels scary. I'm part of one
thing that open cloud achieved. And then for many people, it moved the AI from this thing that's like nebulous and scary into something that is fun and weird, you know, lobsters and all of that. And they'll keep pushing there. Keep building a great ecosystem of open source software. With events that bring people together and with education. We have 10 people now in payroll.
We're hiring a few more roles, including a CEO. Second of all, I kind of make clawing down. You know, capacity dropped to open. Sathya says enterprise grade clause in Microsoft's keynote. There are 33,000 claw named repositories. If we have an assimilation, we're certainly in one
of the weirder ones that won't get shut down. I think it's part of the future. Third, we still don't have an agent that's always on, always thinking. There's still so much to do. The landscape and the tech in the AI are evolving faster than the software that we build around. And that's an
opportunity for all of you. Our workflows are also evolving. Like the vision I had early on, where we shouldn't think about the session or the compaction. The world is finally getting to a stage where this is becoming a reality. We're entering a world where we finally move on from the text, text-only interfaces to voice and multi-modality. Just yesterday, we got a heck of working that your
claw can now facetime you. And this is kind of what matters why open-clo exists at all. Every lab will sell you an agent. Open-clo is the alternative. Open-source runs everywhere, works with any model.
And if you run local models, your data never has to leave your device, your agent, your machine, your life. That's not even my thesis, that's Gary's, you know? We just chipped it first. So, we also finally are building open-clo is open-clo again. But this time with a twist, where everyone sees each other's session on a team server. And there's a claw that knows what
everyone else is working on. And also can also take over orchestration of the work. Then we are finally leaving this slowly. This will be a blip in the future where people work in terminals and run around with their laptops open because their agent needs to keep working. If you only remember three things, number one, don't stop having fun. Find the ultimate driver so you can get the best ideas.
Number two, listen to your gut. And also fix the things that annoy you. It might just become the next big thing. And number three, stay focused. You know? Another podcast is not what will make you win.
Live in the future, build what's missing. And then they write your arbitrary, keep shipping and confuse us them. Now these are five questions. I'm sure you have many more. And I was thinking of plenty of time, uh, 4QA. So first it was agents, then loops, then graphs. How are you building these
things? I mean, it was always sessions, right? But in the beginning, you had to like actually care that like, you would clean and like, you would make sure that your instructions are coherent. And these days, it's more like my sessions are topics. Clearing your session, sometimes even a disadvantage because there's so much information in there that helps the agent. Um, but the big thing,
the big thing, the big thing that shifted is I tried to make the agent more proactive for me. So when I, when I shift my attention to something, I don't want to read issues. I want to see fully reviewed and test the PRs. Maybe I like the feature. Maybe I don't, but like, I don't want to like split my attention. At the same time, it worked. If you come to me and you, you tell me this
feature idea, I'm going to get mad at you. Like it's so easy that you just discuss the feature here with an agent, you build it, you make screenshots, you let me play with it. That way, if it's good, you can like, you need an iter in it. But most of the time, people will figure out why it's not good, and then you come to me. What comes after graphs? And what's next for open claw? I know, like I,
sometimes I like to chip post on a Sunday and then like my Twitter explodes. But also it's not a shit post, right? So anytime you, you know what we as engineers did for the longest time, we built automations to make our life easier. That's like, that's been going on since our profession exists. So if you design, call it loop, call it graph, call it workflow, it's kind of all the same.
If you design something that gets a trigger or gets an input and does something for you, and maybe there's a decision in the way, boom, there's a graph. It's not, it's not magical, even though like, you know, I favorite that some of those graph engineering posts, because I'm kind of curious what their opinion is that it would be. In my world, it's just like, it's just a better way of our automation story that we did for so long already. In a world of build fast, ship fast, how to make sure that what you build is still reliable and scalable. Yeah, that's the part I messed up for a while. Because I was not, I wasn't focused. And the models
were not really good at testing. I think that the models are really good now. We have, we not just have sessions that remember, we have orchestration trained into models. So they really understand and know to use subagents. We have computers, we have browser use, like all of it together is like a perfect Q&A environment. Like I did a yesterday where I spin up codecs,
used for subagents, understand my project, break it down into features, and then each, each subagent would like stress test the feature or code review feature and then inform the other session where to focus testing on. So I'm, we're not at the point where you can automate everything, you'll still, you'll still need to do some manual fix rules so that you know how it feels. But like for a lot of the, the typical box that uses an encounter, you can actually, you can prong your way and you get very far. Okay. AI tools. What's your decision you made purely
for speeds early? It is still with LIFIS today. I think that was really early in deciding that I don't read all the code. I see code review more as a S-risk management. And sometimes you touch a system that is scary. You kind of want to like read a little bit closer. Other times
you build UI, you don't really care how you are, is it correct? No. So you kind of, you glance over or you simply, you simply accept that it looks right. Part of it is just like, you develop a little bit of feeling how long something should take. So if I do a small tweak, that should like change how dragging works and it takes three hours, I know something's wrong.
I'll look closely. But otherwise part of code review is simply like observing, looking how big a change is interesting or good. Okay. AI tools make it easy to build a product in a weekend now. But building isn't a hard part, getting people to use this. How would you go from
the working prototype to your first 10 releases today? Well, I think it was part of what I addressed in my talk. User number one should be you. And my users to the 20 were friends. So I'm sure you have some people that would actually test yourself, but you need to be the first user. If you don't,
if you don't get excited about your building, it'll probably not make sense. Like in this day and age, eyeballs are kind of the most expensive currency because building something so fast now, how do you balance solving issues that annoy you and make features you think people you want? That's a hard one because oftentimes it kind of goes together. I get annoyed if something's not there if I want it. I haven't, I haven't, to be honest, I haven't fully figured that part out yet. I feel
I could just work for months on issues because there's always going to be weird edge cases in software, especially if you add more and more features. But then again, if I only do that, I'll lose interest in working. So it needs to be like, it needs to be a healthy mix. If you could back and change the one thing about Open Claw, what would you change? I would be less stressed out about security researchers. They are really good at making you feel really bad. They would send a report,
they would email me, they would call me, they would do everything they can possibly get to get my attention. But not actually to have a product. In most of the case, it's really just for them to get cloud, for them to get a point, oh, we found something. And most of them really sent reports that they are agent produced without actually even testing it. I would, I would take a stronger sense of explaining what are the parts that we guarantee and what are the parts that will not be fixed because that's not our security boundary. But I honestly, I had no, this was my first time I was exposed to
this world. So I just didn't know how to handle that. And I lost a few months and got a few great hairs to learn. What's the single biggest bottleneck in today's enchanting infrastructure? Reliability, tooling, memory, evals. Managing compute, if that makes sense? Like, if I run one test locally in my
machine, TS-core will spin up 16 threads and will bottleneck my machine. If 10 sessions do that, two of them will probably time out and we'll have to do it again. And there's no real good system of managing all of that. Now, if I do that stuff, it's easy to create a cloud session. If I do like something that requires mequers, that's where 99% of the tools fail me. If it's something that
needs other stuff that's on my computer, same. And you haven't really built something where things could easily move from here to here without issues, at least I didn't see good stuff working yet. Or where I could drive a fleet in a reliable way. Like right now, I use too many systems, I screen share into some computers to distribute the load. I should be doing that. How do you keep an
open source project opinionated and pointed in one direction? Whether they're just merging the N plus one PR that adds a random feature. And how do you communicate that direction to the community? Have you ever said no to popular PR because it pulled the project off course? Yeah? Yeah. I would
say I didn't say no enough. This is when I do new open source, I write a vision.md file where I can't explain what it is now, where I see this to be. But of course, it's incorrect. It's not perfect science. And it's something I need to adhere to better because it is always tempting to add this one feature that looks really cool. But what you rarely think about is when you merge this feature, it really means
here's this pile of code that I don't need, that the person probably doesn't really understand, that I also understand that I also have responsibility. When you expect to have clause that are perpetually running, that are proactive in their work. I mean, honestly, that's not so much a tech problem. It's more a token problem where we could do that today, but you wouldn't get very far with your subscription. And not everyone is willing to spend so many tokens. It's also, but the part that's not easy
is designing a system that doesn't just burn empty tokens. Even the, my early system of like heartbeats was too static and not, not proactive enough. And then especially bad if you have a large session. And then one hour later, you call like a heartbeat checkup and everything. And that means you send 600,000 tokens back to the server after the KV cache cleared and you pay a stupidly amount of money for a lot of not useful work. So there's a lot of things that can be done to optimize that.
It's also really, really hard. Can you tell us more about your own personal setup? What do you host your clothes on? But more like you're running, what harness do you use? Do you still read?
Let me scroll? Do you still read your code? I use my, my MacBook, but I usually use, jump desktop to screen share into my studio and then just use the computer there because that one's always running. That one, I can run whatever I want fast and I'm not doing my battery and I can close my laptop and things keep working. And I have a few other remote machines where I sometimes be in the part that's really nice about it. It's because I do a lot of next software,
agents have to take over my screen and take around. And if you put that in their own machine, it will not bother you. Otherwise, you'll find this agent for the mouse cutter. Do you just read your code? I think I answered that a little bit with the term risk management. And also, if I do open source by
myself, it's a different risk management that if I do software at OpenAI, where we do still read all of the code. Peter, how would you approach your next startup idea? I don't know, should I tell this to everyone? I feel like it gets a lot of copies. I mean, the most important thing is you need to build something that you want to use. Otherwise, it's just not going to be good. Second of all is,
I hope you worked on your personal brand and on visibility because in this day and age, there's so much noise out there that your hardest problem is not the tech, it's not the software, not even the people. The hardest problem now is getting eyeballs. Maybe I would pick something again that's in the category hard and boring because that's usually a category that is a little bit easier to actually find people that will appreciate when you're soft something. If you pick something that is fun, even if it's hard, you're going to have a very tough time, especially in the time where people can just prompt things into existence. All right, last one for today. What's a product you
want someone to build? You know, I feel it's very easy to have to get a test box for Linux. It is unreasonably hard to get one for Mac that works really well. And all the stuff that I got for Windows is also quite annoying. I haven't found it really good provider yet that does all of that fast and cheap.
I'm not sure if this is the piece you want to be in because DevTools are inherently hard, but that's something I would love to have. Thanks, everyone.