From zero to NanoClaw (Interview)

What's up friends welcome back this is the change log. What of the most important viable thing you own your crown jewels Was code you just gave away for free the same weekend that you wrote it well This week I'm talking to Gabrielle Cohen the creator of nano claw about exactly that bet We discussed why restrictive open-source licenses are pointless in a world where agents can rewrite any codebase in 12 languages overnight How he sat down with a cloud code that didn't even know open-claw existed and built nano claw from a blank slate the moment Carpathy tweeted and shut down a marketing agency doing hundreds of thousands in AR And Gabrielle's vision for a human-centered future where every knowledge worker becomes a manager of hundreds of agents heads up I'm going to live show with Taylor Otwell at recent forward check it out at recent comms forward and I hope to see you there a Massive thank you to our friends and our partners at fly.io. That is the home of change love.com your agents in the computer And that is what they built learn more at fly.io. Okay, let's do this Well friends this episode has brought you by friends at coder.com secure environments where developers and agents work in parallel And I'm joined by Nikki Pike field CTO 4 coder Nikki.

What is the field CTO? So I get that question a lot and it's you know half the people understand it have people don't so field CTO I describe it very simply as we're dev rel for the C-suite So we provide a bridge between the customer voice between the C-suite and the managers and the leadership teams of our customers back into our product And then we go through and we help enable our teams to have the same message to make sure that the message is correct And that we're building on something that people actually want not just something that we think they want. Okay So we're taking the laptop away from the developer not really though We're putting them in a cloud of environment a secure environment where they can work with their agents in parallel These are blessed environments. What's wrong with the laptop?

The laptop is the is the trap here and not only because the fact that it could be stolen you could lose it It breaks and you're out of work while you wait for a new one But there's also just the consistency you got there We all know developers developers are going to be looking for some of the latest and greatest and if you're not really controlling how they get out there That's where you get this it works on my machine It doesn't work on production it doesn't work anywhere else because you don't have that consistency you don't have that ability to really standardize What that environment looks like and this is a problem not only for new people coming in You know the onboarding statement is it average I think it's like four to five weeks for a new employee to really get their local laptop set up and ready to start doing the first time A code and you know the time to first commit is a metric that almost everybody knows and the reason they can't do that is because there's a Lot of tribal knowledge out there. They got to go talk to the developers What do we use and where do we get our dependencies? Are we getting from public? Are we getting from private repositories?

But there's also the security and the supply chain aspect of this when you have local machines out there look at like the shy Houlud, you know that virus that went out not long ago This was a compromise of the MTM public repositories They went and downloaded things MPM did what it did next thing You know you're compromised But when you use something like what we're doing with cloud development environments Then you can mandate and you can put restrictions on there to say hey You can only go get your packages from our private repo those packages are expected to have been thoroughly vetted We know that they're clean now does this stop everything like shy Houlud know if that compromise package gets in your private repo You can still have that but it really reduces the surface area of the attack and it also reduces the blast area of the compromise It happened because if your laptop gets compromised and you have to kill the laptop for whatever reason That's weeks out of work while you're either fixing that or you're getting a new laptop Then the cloud development environments allows you to kill that start back up fresh and you're back and running in five minutes You don't have to wait all that time Well friends the first step is to go to coder.com install coder self-host environments your teams to enjoy to standardize around and it's open source So you try out today once again coder calm So we're here with Gabrielle Cohen creator of nanoclaw one of the many claws and you might even say from back back of the day Claude bought started this all right like it was It was a pretty interesting time wasn't it called Claude but when I was called initially this sort of set this all off back and like January February this time Yeah, when I when I found the project it was called Claude but and then it became multi-bot for like two days right then open Glo what do you think about the I guess the direction of the name even like just get into the world of claws? Yeah, it's it's an interesting name. I don't know. There's something about it.

That's a little bit Little bit playful. Maybe a little bit aggressive But I think with nanoclaw I tried to take it into more friendly side and and I think the names does that a little bit also our logo this little blue lobster cute guy instead of an angry red guy Yeah, I know the the red is kind of angry is not blue is a bit more color science right like a Soothing aren't aren't most things that are blue kind of soothing water soothing right and then that how they get to associate it's all like that I think so I think brands that want that want you to trust them. Mm-hmm. What do you think about the state we're in with?

I guess how drastically things have changed and at what point did you get inspired by the work of Peter So I'm very good. What was going on there to then create nanoclaw like what how this trailing for you? What's your journey here? So I actually started to play around with open claw in early January I downloaded I set it up it didn't stick for some reason and then end of January I Came back to it.

I'd been messing around with I actually got a Mac mini. I was just running background cloud code tasks on it And then but I was looking for something that gave me a bit more of like ability to schedule tasks in a nicer way and cleaner way And then so I came back to open claw Set it up I was building at the time a I native marketing agency So using agents for all kinds of stuff content optimization and whatnot and then I just set it up and Gave it access to an obsidian drive that had files for each of the customers that I was talking with the customers at sign And I just set it up there and I said you are my sales manager and you manage my sales pipeline and just figure out a system for doing it and You know basically that's it and then I connected it to what's up group with myself and my co-founder and it started to send us morning sales briefings sales standups each morning and Updates and whatnot and I was like this is wild like within a day was doing the work of person doing it quite well Interesting. Yeah, and then I mean that was working and I was like well, okay there's actually real value here which was surprising to me because I was like it's just I've been using club code for a year then and you know coding agents were a little bit longer than that and I Didn't really initially understand like what's actually new here that I didn't have before and it took a little while I spent like a week trying to figure it out But I saw some security issues I saw some problems that concerned me as I was setting it up and started to use it and I didn't feel like it was production Was production ready open claw so and I wanted to build a business with lots of agents running on top of it So I just sat down and set it to build my own project which became nano cool What was that process for you where you I'm not familiar with your full history you mentioned marketing agency Help me understand how and don't take this as a majority But how developer were you prior to this like were you deep in development? Did you learn on the job?

Did you learn as you built in a colleague? What's your developer journey when it comes to this? Yeah, I was full developer before this I so I studied physics and computer science you wrote code by hand yourself Everything many lines of code with these fingers. Yeah, I study physics I study physics and computer science at television first.

Yeah, I didn't learn how to code in university I just learned like you know how to reverse trees and stuff like that but I worked at wix.com as if for seven years and was a front-end developer full stack developer and led a team of developers there and I so I'd actually stopped doing development for About four years I took off from development. I When you work I mean you I'm sure you've seen this you work as a developer for a while at some point you start managing people and then it stops becoming software development and it just becomes managing people and I got to a point where I felt like any time I was writing code It was because I was procrastinating from like doing some something I was supposed to be doing and it wasn't as much fun anymore So I took some time off I spent like four years doing public relations working with tech startups a lot of cybersecurity AI ML and and dev startups and helping them really really technical companies helping them talk about Super in the weed stuff in a way that would be understandable by why they're already in some resonate and get reporters interested in what not So I spent time doing that and then started to build an AI native marketing agency as a new business And that's how I got to to open claw and then Yeah, it's a real bummer that that's how the arc was I suppose I'm not sure what the arc is now do we Do you do software development now? I mean you're kind of back in the same realm Right? You're sort of managing agents which are like people so you end up managing things or entities or whatever You want to call them to do the coding work, right?

And so you're kind of back in this manager job. Do you feel that or do you feel like you're still close to the middle? I Feel now. I mean, it's a really good question and I think it's we're still figuring it out right where this is all going Definitely not at the end point yet, but the way I feel now is Not like a manager because I don't have to talk to people about you know taking their time off and how they're feeling and like Motivation levels I do like to get my agents motivated.

I like to be like great job guys Like we're really on a roll here, but and I think there is a little bit of that management thing that works with agents But it's more my role as a software developer. I feel is more of an architect so giving the big vision and the design and They're implementing it and I know I guess for some developers I don't know how you feel about it for me. It wasn't so much about the you know writing the code typing out the code I never got really good with you know 150 or whatever words per minute I was always a bit slow at the typing and took time to think about things and I think where I brought the most value was in figuring out what we can cut out and how we can simplify things and write less code so I Like the role of being an architect rather than type not code. Yeah Let's think into that because I feel like that's That's what we're all kind of moving towards right and for those who don't really have that architect brain Or just like the natural tendency to like architect things.

That's what I naturally do. I think Anybody who's been a product manager role anybody who's been in a UX designer type role front-end role I suppose many developers to your problem solving, but are you always architecting? I think a lot of those roles really lean into this Architectural kind of feel I feel like I do a lot of this like I suggest intent I suggest Not every single detail of what I'm trying to build with an agent for example But I end up kind of giving the world I want to live in what are some of the things that are true about the world You know what are the things that are untrue about that world, you know what are the do's and don'ts and it's it's kind of like taste But I think it's more like architect and intent and what should happen and I think a lot of that stems from like understanding user experience Or even just workflows and problem solving I think that's the world we're in now is like is that the majority of folks are building that way? They're becoming architect versus you've been manager.

I hate being a manager of things. They're other architect things. What about you? Yeah, I think there are I guess like you're saying multiple roles in managing agents I think the baseline is you have to be able to manage them, but then there's the role of the architect there's the role of the UX engineer and product and I think you have to have another kind of like to stand on besides just I know how to manage Coding agents.

I think you got to bring something else to it, but it could be it maybe doesn't have to be the architect. I think Yeah, the agent manager I mean we're going to a place where it's like agents managing agents when you kick off a workflow with fable 5 in many cases You give it a very basic direction and it goes off for hours and managing all the agents and orchestrating them so I do think that the engineering and architecting probably is shifting to like you're mentioning the Architecture architecting the world that this agent lives in and the feedback that it gets and what's true for it and what it knows and sees Rather than telling it how to build a software and and I think that's the next evolution to me The when people are talking about About loops and building loops and whatnot for me. It's about it's not about a while loop It's about orchestrating or engineering some kind of architecting some kind of feedback loop, right? Gives the agent signal information about what to do and what build.

Yeah That's kind of fun I still haven't perfected and maybe you have with your work this idea of loops and this idea of cues And I've you've heard lots of things with folks suggesting this is the era of cues and loops now That's what we should focus on not to prompts or prompt engineering more like context engineering like you have enough context build up So I get to say go and do it and that small go and do it phrase actually has so much context behind it. I feel like Something I experienced recently was just having one agent talk to another agent and how that agents context and its role as a reviewer Maybe a PR maybe it's a code of use something like that Kind of re prompts the initial agent that's actually leading most of the work the one that I'm architecting with the one that has The majority of the plans context and the one that's in charge so to speak of the one or many subagents like that whole loop of not Just the context you build up by documenting what you're building or thinking about it and architecting it like that But that a sub agent or a side agent can then go into a code review or a pull request review or something like that Which re prompts the main agents like almost a Getting in a way where it's the fish eating the fish tail kind of thing where it's like if you kind of keep this dance going with one Prompting another as long as your context is true with what you would try to architect well, it's on mission Now you don't need a course correct it really at all it goes I think that's even more true or maybe more true now with fable five and these new class models where they seem to be more capable now of Open-ended kind of work where the task isn't very well defined and it requires decisions and judgment And and I think that is starting to become the reality where you can you can give it maybe more like values and principles of what your preferences are and your tastes and your choices and Then let it reason from those principles and values about how the song should be designed I think it probably will become more important for projects to have have those kinds of documents like it's called MD I think is probably gonna go away in terms of like use this kind of limting thing or use the you know This pattern when you're writing on functions and instead it's more like what are the what's the ethos and values and principles behind how I want to build and what we're trying to do Yeah, how long did it take you to get to something that was usable like how long did you not sleep did your Family miss you did you stop eating what did you turn into an AI vampire like this famous or infamous phrase comes out? Like what were the initial nano collodays for you when it came to building it and how? Did you I don't want to say this maybe like did you copy?

Ideas from open claw or did you say you know what I got my own ideas? There's some good ideas out there, but I have a plan that I think will work better. How did it begin for you? So firstly I took five days roughly where I had open core running and I had seen what it could do And I spent like five days I was going to work taking showers walking the dog but all the time in the back my head I was thinking like what what is this new thing like what what did it unlock?

Why is this interesting? Why is it suddenly bringing all this value when it's just running a coding agent? I already had the coding agent like what's the unlock here and I spent a lot of time thinking about that and then Sat down to write the project once I felt like I had a thesis let's say about what what those things are and it was like I don't even know if I remember now, but it was like I need memory. I need a persistence session I need it to be connected to the browser.

I think turns out browser is probably not that critical and I need it to be in a messaging app. It's like a big I think psychological shift when you're talking within the messaging app instead of in the terminal and it's just also the availability is always there There was maybe and then the extensibility the fact that it could like add things and the schedule tasks So being able to schedule jobs for itself that makes it feel at least proactive like it's Coming to you to update you about stuff instead of you always going to prompt it So I had this thesis and then I did you know do one of those crazy marathon coding So I sat down Friday night in my sweatpants on the couch and this couch here behind me and And basically like melted into the couch for the entire weekend till Sunday night I think probably about 40 hours of like of coding And my wife was like I haven't seen you like this for like 10 years since you were in university This is like something wild is going on but to her credit She like let me go down this rabbit hole and and It's like something's going on and left me to it And then I came out on the other side so it was Sunday and I was like if I don't release this now I'm gonna spend the whole week on this instead of doing my real work, which is building my AI native agency So I just said I just got to release it put it out there Mostly AI generated read me which I got a lot of grief about on Hacker News But but I published it and people you know it took off like pretty much immediately I just posted on Hacker News and it started to take off and shot up to like Thousand two thousand stars within the first day and I know I had seen projects go on Hacker News And I knew normally they go they shoot up. It's like the reverse hockey stick So they like take off and then they just flat line But this kind of kept going and it went you know 500 400 500 stars per day and it just kept going to 8k 10k stars and then a couple so spent like Two weeks back and forth my co-founder going should we keep building this AI marketing agency that we built or should we become the nannical company? and going back and forth on it and Starting together that okay, let's give nano clot another two days Let's invest a little bit more in it and kind of kick the count down the road and see where we're at in a few days And then about two weeks later after the initial launch car path the under car path He tweeted this whole post about claws his claw post and half of the post was about nano clot And now he thought it was mind blowing or slightly blue his mind and and then it just went to another level and wow It was like clear.

All right, we got it. We got to do this So we went called our customers at the AI native marketing agency and said sorry guys I got to drop you we've got this new thing and and just shut down we were ramping up very quickly We were at a few hundred thousand in a rr and like really good ramp I'm right and we shut down and created nano co as the company building nano claw. Wow You know right away you would build a business around this. This wasn't by accident.

This was totally What we call premeditated? No, not at all premeditated. So I built it just to use it for myself I so I put it out MIT license I would probably make that decision again if I if I came to it but I didn't even think about it because this was just it wasn't even a thing I spent two days building it. I was like this is there's nothing special here Like if I spent two days anybody else could so I just put it out and thought People find maybe people find it useful And maybe they'll contribute to it and then it will make it better and I could use it for our own business Get it more more robust more stable And I thought it would be good for our reputation as an AI native agency to be you know to have created a successful AI agent project So that was my thinking but it was totally just gonna be the side project I put it out on my personal GitHub user and only moved it to our companies GitHub after it took off It was just a weekend project.

So you shut down the agency pretty abruptly though, right? Nanoco, you and your co-founder Did you I guess there's a lot of context I need to build up to to ask this question properly There's a concern I suppose at least I know I had the concern and I hear other people having similar concerns around open source And then you mentioned you open source right away as MIT which is the most liberal open source license like you would actually say that is truly In the spirit of open source that is open source just having the code open visible is not obviously open source The license that gives you permission un-fed permission to do what you want. And so here's you you got this, you know Friday the Sunday 40-hour marathon you release it on Monday because you're concerned about how you'd actually do your job money if you're Friday Which I totally empathize with because it's so tantalizing when you can just do so much and your ideas just kind of life in front of you It's kind of wild You said you would consider or do that again with the MIT license How how do you can how do you think about or reason about open source in this world now where? Even if you'd written let's just say you'd written it something in TypeScript and I want to borrow an idea and I have a go program I can easily look at given with agencies days.

Just look at what you're doing and and graft intent off of that not so much Take your code or take something like that that would have normally been licensed intellectual property, etc Even if it's open source it's still some version of an IP even if it's permissively open IP It's still IP How do you feel about that decision to go the MIT route? How do you feel about the state of open source and is your position currently in any way hindered and maybe you can't even say yes Or know this because you're already on this road man You can't you can't put the cat back in the in the bags of the speed because you already open source in MIT licensed in a claw How does that sit with you when it comes to? You building a business around a code repository. That's fully open with fully permissive to any degree anything about that Yeah, it gets right to the heart of I think the difficulty big that's going on.

Yeah Yeah, I think it's not a difficulty for us surprisingly and it I'll explain why but it's clear that open source I don't I've heard people saying open source is dead. I wouldn't necessarily agree with that I think though it needs to evolve, you know kind of Metamorphicize into something else. I don't think open source the way we knew it before Works anymore is going to continue, but I think there is a new way of doing open source new model for it. I Yeah, the project I put it out there and people started to use it and teams started to use it and And companies started to use it so there are companies that I know of and I've been in contact with that are building their own internal agent platforms on Nano claw using this infrastructure their teams building on it their companies who are building products on top of it and and And providing services with it and all of that is fully allowed with the MIT license and I actually am happy about it and endorse it all And I saw even within a few weeks of launching it There were these sites popping up like host your own Nano claw and providing hosted Nano claws and I'm fine with that We're not we're not going after that kind of business I Think even if you chose a different license today You chose the most restrictive license once the code is open source like you said you could just tell it to rewrite it in different language And people did that with the I think it was cloud code source code that leaked allegedly or That's what people were saying anyways, it was cloud code source code so it leaks and People posted on github and then there were all these takedown requests so then people had AI coding agents just rewrite the entire thing in Python in Rust in you know 12 other languages and that actually Once you rewrite it in another language the original license doesn't apply anymore So you can look at a project and rewrite it and that's fully allowed by by licensing So I think it doesn't really help you to have open source that's restricted license You might as well just go all the way with MIT license and get maximum Reach I don't think the model of building an open source project and then trying to monetize your own user base Works because it's so easy to host stuff.

It's so easy to fork it I think the new model is the open source project is just about Building up a brand getting a community getting distribution. So that's the way we're looking at it for For nano cloth, so we've got people building a nano cloth individual businesses. That's all great only 1% probably much less probably a 10th of Percent of companies are gonna build their own internal agent platform on top of an open source project Like even if they have the engineers in the company who could in theory do it They don't want to take their best four engineers and put them on building an agent platform for marketing and for sales They want their best for engineers building their own product the core product and we've had those conversations with with companies and you know They're very clear about that. So what we're focused on is providing exactly that in agents It built on top of the non-open source project But with a lot more going on on top of that for the 99 plus percent companies that are not gonna build their own internal agent platform So you need you can't just put agents in sandbox and connected to messaging app Even if it's really good sandbox and great orchestration and great project and roll it out in enterprise and fortune 500 company You need to be connected to identity you need governance.

You need audit you need To be deployed into the customers into the companies own cloud environment with Retention policies and logs and a whole host of other things So that's what we're doing providing for them together with services actually going back to where we started of AI native Services business so providing the services of figuring out what they need What do the agency look like what should the policies be around what they can and can do and helping the company guiding them through the process of rolling Out agents that are really powerful connect everything like we know about open cloth But controlled safe secure and doing responsible way. I like your view On open source. It's intriguing at least I want to hear more and so if I understand correctly Your position is that open source has obviously changed even at the license is not permissive the fact that it's there Might as well be permissive because anybody who has any sort of ill-feeling whether it's like towards you personally towards the project Or just like you know what I'm gonna take what's here and just kind of run with it and build my own that was never really a customer potentially Anyways or I never really thought about like that like it used to be open source used to be about sharing an idea Getting people together around it. I suppose that's still the same if your view on open source is true Which is it's about building a brand about building community and then but then how do you then say to that community?

Well, I've been giving you this offer for free. I and any other contributors whether it's with skills we can talk about later We're actual code. I guess cool to contribute via skills You were contributing you're using for free And now here's a paid product that I want to sell you or I think gives you value So therefore because you accept the value maybe you'll also accept giving me the exchange of value Which is monetary value? It's not a commercial capitalism works if you didn't know that I'm pretty sure you do that's Not drastically different than the original basis that I've been kind of operating on a round open source But it's uniquely different because it seems like you just have no fear on The exposure of let's just say your crown jewels.

No clock, right? You gave away the most important the most important I'm air-quoting boy the most important asset How do you then take that and commercialize that in a way that? Doesn't hear you I guess maybe haven't gotten there yet. Maybe you have doesn't seem so from the outside, but how do you how do you reconcile?

MIT open source build a community build a brand and then find a way to Commercialize on top of that without your crown jewel MIT licensed project Sucking the life out of you in the process. We have it's a word commercializing. We have we have customers we have pain customers and I Don't know if the same will hold true for every project. I think a claw type of project personal agent It's a unique it's a bit of unique thing.

It's not a developer tool, right? Which most open source projects are it's mostly tools for developers platforms for developers infrastructure for developers This is something that anybody can use and you don't use it for building software you use it for your personal stuff and So we've got this big user base We've got tens of thousands of people that have set up their own personal system for second-brain the Minister of Foreign Affairs of Singapore Has been very public about being a user of Nanaklo He's described this whole setup and published about it and many executives at large corporations Our companies are our users are posting about it on LinkedIn and posting about our necks and then what's happening is those users They're seeing a lot of value like other people have seen from open claw But for them being a bit more you know security conscious or wary they decided to go with Nanaklo They see the value and they're saying I want to give this to every person on my team every person in my organization So they get the same 2x 3x boost in productivity that I saw actually outside of work mostly in my personal life because they weren't able to bring it into work They didn't have the you know all the compliance stuff and and other things they need to be able to bring it into the company But they set it up on a personal email They see the unlock they want to bring it into business and then they started to reach out to us saying hey How can I roll this out of my company and the same thing was happening with individuals on a team? Smaller teams who were able to set it up within their own team This one guy he's you know, he's an investor and a VC firm He said it up for himself He's using it and then other people at the firm are coming to him and saying hey Can you set me up with an agent as well and he approached us and said hey? I don't want to be the IT guy for my company now who's helping everybody set up their agents I want you guys to do that so so the Open-source project the open-source user base and community becomes a pipeline for deal flow But it's not us search cannibalizing or monetizing or extracting value from those same people who are using it if you're using the open-source project I'm not trying to turn that into a paying customer It's if you're if you've seen it you've seen the value you love it You like it now you want help bringing it into your business or your company and you don't want to do that yourself If you're using it as an individual user and you want to be the IT guy for the company who builds everyone's agents Go do that as well.

I don't want to monetize that either I think at some point we may start to feel a poll from companies saying hey We build our own internal agent platform and we want you know some form of support or some form of this or that but for right now I think the biggest opportunity for us is actually 99% of the world that is not gonna use the open-source mmm interesting So is that the kind of business so while I recognize the commercial opportunity here and maybe that's just the surface that We're scratching and that's what you can share here now Is that the business you want to run because I mean to start out you began as an engineer Building software kind of ejected from that did something different for a bit came back to it I'm paraphrasing a lot of your story So fill in the blanks and then one of your angst was managing people and not Architecting software it seemed like that was if I'm rocking your story That's what your angst was and now here you are running nano go which largely seems support esque Like let me help you set the thing I made inside your company. Maybe that is architecting help me understand What's interesting about the potential future? You can forge and and clear out with with nano go is it just support? What are the bigger opportunities here?

It goes beyond support and it goes beyond the services are on the setup each When you look at a large enterprise fortune 500 company So they need to connect to their identity provider So they can define rules and policies not only for users but for groups And those need to match up with the groups that have set up in their their IP they need to be able to set Policies so they can't just set let each individual user decide what their agent can do We can't do they want to set it up in a controlled way across the organization access control policies of what each agent can do So for example, we're gonna let everybody in the company connect their emails We're gonna let their every these agents if people want read the emails search through their emails But if the agents want to send an email across a whole company that requires human-loop approvals, right? And then we set a policy in our organization agents can't delete emails. You know you want the you want to keep keep the information you don't want to delete so That's something that you can't do just having the open source project and deploying for individual users there's another level on top of that which is really about governance and Beyond that there's the process of rolling out agents working on organization You need to have templates for what kind of agents are we to have marketing agents sales agents engineering agents? They need to have instruction skills policies tools are connected to recurring jobs.

You want to give people an agent that's valuable in day one and So there's there is software there There's a platform and then there's the services around getting it set up and around managing maintaining it in the long term but with Coding agents there's a new opportunity here because things that used to be really intensive labor intensive require a lot of Human hours of work can now be done by agents and be be automated So a lot of those services for example when we're rolling this out to a company We're gonna roll it out to say start with a small group of 200 people in the company We want to gather information for them about what are their workflows look like what tools do they use? How do they use those tools so that we can set up the templates set up the policies we need to gather a lot of information? So rather than you know doing human interviews with people or sending them forms to fill out that they're never gonna fill out We have we put them on a big group in a big slack channel And then each person gets a DM from an agent our interview agent and it starts asking them some questions about what AI tools do you use? How are you using them and it gathers some information from them and then based on that information?

We're able to come back to executives to leadership in the company and say here the Templates of agents that we think you should have and here is a reasonable starting point for your policies Here are the tools we think you should connect them to and you should connect them to and some more workflows will build and then I Think fundamentally what we're building is not what we're doing is not providing a service for a company to deploy their Their agents within the company and then maintain them over time What we're building is a factory an agent factory and the output of that factory is custom deployments for large enterprises Those change the cockless quite a bit I mean when you were saying about interviewing people and getting into the details I think I should spend a lot of time on site talking to Sally or talking to Bob about their red stapler whatever you know and Then here you just go and change it and flip the script and say let's just put a lot of slack channel and have the agent DM each Person who matters and interview them. That's that's a different thing. Tell about this agent factor What is what are your big ideas here for agent factories? What is the what is the status quo currently?

And what is the future we're driving towards? I think it comes back a little bit to the skills thing of contribution and and what You know that really defines what our agent factory looks like so When I sat down to build nano claw I was I was really I'd gone down this rabbit hole They I native and like AI changes everything AI changes how software is built and written and a lot of the old rules Maybe don't apply and we got everything everything So I sat down to build it and I thought I'm gonna build this as an AI native open-source project or AI native software So part of that was initially when you want to set up nano claw there was no wizard there was no installer There wasn't any documentation even for humans have had I set it up? There was just a skill slash setup and you run clawed in the project directory so clone the project run clawed in directory and Do slash set up and then Claude sets it up for you And if you wanted to I shipped it initially just with WhatsApp and in the read me it said hey I shipped it with WhatsApp because I'm using WhatsApp and this is my agent But you're welcome to use it and if you use a different messaging app Then just run clawed and tell Claude to change what's up for another messaging app like that's the way to customize And I said don't open PRs for adding slack and adding discord I don't want to have all this bloat in my project But if you figured out how to make it work for yourself with slack your coding agents figured that out for you instead of everybody figuring it out From scratch As your agent to kind of put together the steps that it did to get slack working to rip out what's up with slack and instead Write those up and contribute those and just put it in the format of a skill because why not you can just run it So contribute back the information that teaches a different coding agent How to follow that same process and how to customize this project so that it supports now slack instead of what's up? So rather I said rather than features contribute skills And we'll be able to keep the code base really small if it's small agents can work in it really well they can one-shot things and then we'll be able to support everything by having lots of skills and That I think a lot of people you know a lot of people's attention because that's just something different that is leveraging agents and the new capabilities that I brings to just do things in a totally different way Friends I'm back with a good friend of mine Michael Greenwich Michael I know that I love work OS our audience may not know about work OS But what are the challenges developers face starting a project choosing the right tools?

Just write database choose them right off take it there when a developer starts a new project The decisions that they make at the very beginning end up having long lasting consequences What language you build in what platform you build on top of what database you choose? These are things that are very hard to change later on So they have like major consequences and especially if they limit your ability to grow and scale at some point as the product starts to take off You're gonna have to stop developing your product features and go re-architect or rebuild your system And that might be a killing blow right at the moment you need to accelerate So these decisions are really on a really really important And I think that's why developers gravitate towards solutions that are mature things that they know that will scale even things that are open source You're gonna pick you know something like planet scale for your database provider Not because it's the cheapest or because it's the you know most fun to use But because you know it's gonna be a durable provider that you can scale on for years and work with us It's like that for off You know at the earliest earliest days if you look across all these different services They kind of look very similar but at day 1000 or day 2000 or day 10,000 You're gonna want to have made sure that you pick the platform that could scale with you And today work with is powering off and identity and security and permissions for all these AI companies literally the fastest-growing companies The world like opening iron and dropping for server perplexity work with us is under the hood there So I think when people pick work with early on really what they're doing is trying to pick the defaults to allow them To grow and rapidly scale and there's no platform other than us. That's best done at the same level Well friends the next step is to go to work o s calm sign up today check it out free for a million active users Try today. There's no excuse not to it is your default.

You should choose it. So do so work with us calm once again work O s calm It's a different world when you think about even where you begin there with like AI changes everything and I don't want to like just gloss over That phrase because it really does change everything whenever you think about Just the flow of information like even initially you mentioned that you had Claude set up right slash set up for example, whereas in today's world the set up is largely human facing which I think is a an interesting choice You know you run bash and then I believe it's like nanocallowed I say to five recall quickly and in the process to sit in a Claw and that's very much a human facing choice process script one. It's just a simple bash script quite beautiful You got your your I guess it's lobsters at a lobster with the clause everybody's using it's a lobster Right a little blue lobster a little blue lobster a little blue lobster. I like that lobster You know you got this splash.

It's very that's not it What I'm trying to say is that flow is not human or sorry? It's totally human. It's not agent although you can eject out of it into an agent into Claude helping you like in my case When I've rusted up it had an issue like one of the containers timed out and thankfully, you know your script wasn't just like oh well It was more like seems like something's wrong here Do you want to have Claude troubleshoot for you? And so I ejected out of the script into Claude and it began to troubleshoot it, you know Look at the logs and turned out I was on a headless Mac where I wasn't looking at the screen and Docker wasn't installed yet And so as I'm trying to figure out what's going on here then I'm like let me actually remote desktop into this you know headless Mac mini and take a peek what's going on here won't behold it's asking me to approve Via the the GUI the graph will use your interface to approve You know like Docker being installed or whatever was you know like I think the Mac OS was actually stopping the agent from installing Docker Because it required a permission and so those are all normal things, but that flow is largely human And it's even weird to even still say that I mean it's not quite it's weird to see on the podcast Suppose but it's not weird to think that it might like brain So my own thoughts but to say that this is a human flow not an agent flow because it's still sort of getting into the world of agents Like this becoming real like 2026 is the year I'd say like 25 began it and it was like right the tail end So I feel like 26 gets to own the year of agents I could be wrong But I don't think so but you get in this position where you're like this is a human floor This is an agent flow and you sort of think about you know I native and and even how I would interface with a particular software that only has human focus flows that has no agent flows I can't have my agents Automated so much changes whenever you think about this idea that you have a native ways and that AI changes everything When you zoom out from that phrase AI changes everything how how has not just your software development life change But how has life changed for you in every way from how you interact with your wife and your family or whatever like how has AI changed everything for you So with the family you know we're keeping it pretty human And I know people are using agents to help them manage things at home But you know my daughter loves not because she's four and she doesn't really know what it is But I got lucky and I chose a cute little officer is a logo So she knows a lot of search loves it you know now claw You know when I can't when I'm home late and she's why are you coming home late?

Yeah, I was like cuz people want to talk what do they want to talk about now? So that's good I recommend if you're gonna start a company she's a cute logo so that your your child can can can connect with it But it's changed things really profoundly I think in in work for a lot of people in person life for me more so in professional life I had a you know a bunch of people join our team. So we're building on a team We've got 15 people on the team now at nano co nano co is our company. That's providing nano co-type agents for large large companies I Have had a lot of people joining the team Juggling a lot of different things so someone was joining the team to pick up partnerships for us And I had been having calls for three months with all kinds of companies and people and I barely remembered any of it So just a smhaze so he came in and Realistically I needed to spend like two weeks sitting with him and getting up to speed on everything and and I'm boarding him and Digging through call notes and emails to try to find all this information for him and instead I said look I don't really have the time for this I Saw it with him for like 20 30 minutes to kind of get him up to speed and how I was thinking about stuff as best as I could and Then I put him in a chat with one of my agents So it's like my second brain that's connected to all the call notes emails everything and I just said actually the night before I Spent like 45 minutes with the agent saying like search for this email thread Like just try to remember what had happened and going from asking to go from my calendar and look for stuff So I pointed it at a lot of the information that I knew was relevant Which would have been maybe a bit difficult for him because he doesn't know what's there So I said okay look at the email threads and then I said this calendar event There's no email thread, but you'll find the you know slack the M thing and this one There's a call and then so it loaded up lots of information into its context And then I put him in the channel with it and I said hey Andy this is a soft he manages partnerships You know help him out and then he just started chatting with it He's still chatting with it till now till till so recently he's you know it's still one of the agents that he works with and he was able to get information about Communications about calls about meetings that I wouldn't even wouldn't have even been able to provide to him because this is just a blur of things That happened I barely remember it and he was able to get exact information with the notes with transcripts of some conversations So that is you know and the same thing with our head of operations same thing with gold market So that's just a totally different process and work for a lot of people on our team has been primarily managing agents It's it's definitely that for developers but for non-developers as well for go-to-market partnerships operations People in the team managing community It's it's just become a process of working with agents And I think that process is really powerful when you bring them in on day one and you say here's an agent And they're gonna help you with the onboarding People start to think about work and approaching things in a totally different way and I think there is that shift of first thinking about how can my agent do this and then first going to an agent and saying hey Can you do this for me?

And then if the agent can't do it stopping to think why can't it do it? Do I need to give it to a new tool? Do I need to give it more information? Wow?

That's wild to hand if I'm just incorrectly you your agents name to Andy is that right? That is all of my agents are named that the yeah, it's like from the guy in the office and for the office That's that's makes sense. I was thinking Andy from Toy Story, but okay Andy from the office is fine too like Andy Andrew Bernard is the best So you're talking to Andy and you're like hey, I got on board So we got to talk I'm in a paraphrase what you just share back But you basically gave the agent the context Information and authority to go and research and find and discover and pull back a layer of information And then you gave it access or you allowed somebody else to talk to Andy on your behalf with that envelope right with that authorization envelope so was there parameters how do you set those parameters is that what you did there where you sort of like Primed it so to speak and say hey Andy go talk to so and so about this and then they can go and keep talking to them as if They're talking to any given chatbot but the the context or I guess the the knowledge base they're pulling from is these email threads and the background story and the details that You don't want to give them access to inbox you want to give them access the information in your inbox and so Andy did that right? That's what happened here Yeah, yeah, that is so it's I put the agent in a group where I was in the group and the person who joined the teams in the group And the agents in the group so all three of us so it's a little group chat I'm not really engaging in this group But I am there and everyone's in while I take a quick look and jump in and correct things if they're not if they're not accurate So for example in in the first day he was asking about one of our partners And he asked information and share with him like two recordings and I was like no there's like 12 Start to transcripts or notes from calls and I was like no there were 12 different meetings with this company You gotta go search via email in my calendar to find all of them and if you're missing notes from any of them let me know and I'll pull them up from somewhere to find them and so that's We had a discussion internally about about access control right data like who should access what and are we okay with With each of these people accessing information that we were sharing and we made a decision to go pretty permissive with access to data maybe a little bit maybe not sharing with them everything but sharing with them an agent that we knew full like full and well that the agent may share with Them certain information that is suboptimal for to be sharing but we made the decision that in in order to be able to move quick It's it made sense to be much more free with information than we would have probably been by default not information that's you know super sensitive customer information or something but just you know you got different people on the team and Think a little bit about what each person should have access to um for for large enterprises That's a non-starter like they cannot have people and agents have access information.

They shouldn't have so Actually some of the capabilities that we built more recently into nano claw are for solving those problems So we've had we've added capabilities into nano claw you have agents agent communication So I could define by default one nano claw deployment one instance of nano claw running in a VM can run many different agents And each of those agents are segregated in and isolated in their own sandbox Which is a hard-end docker container and they don't have any access to information that other agents have access to then I can by default They can't talk to each other They're just happen to be running the same box and the same VM say the same machine But they have no visibility into the fact that there are any other agents running in this VM But you can wire them up and say this agent can talk to this agent And then they get injected into the context the name of an agent that they can talk to and then they can send messages back and forth and The orchestration layer of nano claw checks if they're supposed to be able to talk to each other Something that we added recently is adding an approval gate on that action So I can set a gate a rule saying that when my agent is talking to someone my team's agent I need to be asked I get shown the message that it's a send and I need to approve it that approval is not It's not a prompt for the agency you need to ask for approval the agent doesn't even know that there's an approval process It just sends messages back and forth in a way normally does outside of the agents environment in the orchestration layer The code non-agientic non-ai code that's responsible for taking messages from one agent and pushing it to another agent that code enforces these policies And shows me what the agents try send and then I can prove reject so with those Wirings of what you can talk to which agent and where there are these approval gates you can enforce data access policies and control and Prevent an agent that has access to any sensitive data from sharing that information with an agent that has access to the internet You get some weeds down Sure, right like how do you how do you manage the the the items that you might get from that the fatigue you might get from approving or Having to review a policy or look at different stuff like I mean it feels like an onion like in terms of layers or so many layers and And that how do you navigate with nimble? I had a man how to deal with such a complex multi-layer kind of scenario like that that seems Hard to put it to put it the most frank way totally. Yeah, I think the onion analogies correct there's so many layers to it and The way with my like architect brain right and way of thinking about things Looking at the problem of how do you how do you build in such a complex space where there's so many unknowns? It's moving so quickly and it's so complicated and every rock you turn over.

It's just this you know Every rock and find a whole world ecosystem this reactor at go ahead. Yeah, yeah So I My approach has been to kind of put these blinders on and say I'm gonna tackle one little problem at a time And I know that there's this bigger There's another layer and then I'll add that but I'll get to that layer once I've unwrap this layer And the thing with AI and agents is there is so much value to unlock There's like the way I've visualized it as I started to as I started to kind of become real for me was like we're walking on the street And there's just piles and piles of like value right you think of it however you want you know candy gold whatever your favorite analogy is your favorite thing is and it's just lying there and in that kind of Spent world reality that we're operating in where there's so much value It's so easy to take an agent and make it do something that used to take lots of time lots of money Have an agent, you know do something that used to be a whole product category And now it's just like a prompt that you give an agent and it runs and it does it for you So I mean my sister is non-technical She's building nano claw to find she runs all these shopping groups with deals and she's using nano claw to Find deals for her and send them into the shopping groups with affiliate links and stuff That used to be a whole SaaS product that someone pay like 200 bucks a month for and now it's like agents give them the right prompt And they'll go and do those things for you. So How do you build in this space? You got to focus on not on solving the whole thing But on solving one piece that's gonna unlock some chunk of value and then once I can do that it doesn't solve all the use cases But if you solve one use case then I can start giving the people getting them using it unlock that value And then I'll hit the next one and I'll build another piece and the next one I'll build another piece So that's our building so I added agents agent realize this doesn't actually work unless you've got the ability to set rules between each It's talking with each other set those rules.

We're setting us and there are certain workflows where it won't work because permission For the agents gonna be paying you every ten seconds for approval You just shut it off But it doesn't lock certain workflows where the agent can do a bunch of work and then you put an approval gate at one or two key points And it's able to show you certain context you can approve and it carries on so we have an unlock everything Even if we don't only unlock one hundred percent or five percent of workflows or the work that people do we can start to bring tremendous value and grow from there Do you it sounds like you might have the same philosophy I have which is to build a thing or building that thing you said you're focused on because you said you know You'll cover this rock you find this ecosystem. Oh my gosh there behind this major thing I'm building is another major thing that has five tentacles that I can go down I can just get overwhelmed as an individual human with a brain a human brain that gets Cognitively overloaded fairly easily if I let it do you think in terms of like okay, I'm gonna build the simplest Focus thing I could do right now not this complexity But the most simplest initial version of it because we can kind of predict this future in a way and get overly complicated But until we've actually used it put it into practice and learn like hey actually agent agents I should be cool except we need we need policies around which agents can talk to which agents and then maybe just because Andy can talk to Dave or maybe it should be Jim sorry about that or maybe a What's the most favorite Dwight maybe it's an end white maybe you know agents agent and you can talk to Agent Dwight but maybe they can't talk about Sales data for example like sales numbers they talk about potential deals But they can't talk about the actual numbers because that gets into the area The point I'm trying to make is that I'm getting the details and just fantasizing about this world is great If you want to end you know And why is when you are focused on a thing you're actually building do you have the mind of let me build the simplest thing first? Play with it and see how it needs to change and fit and grow and more for how do you how do you approach? You know agent agent messaging for example and then go from there.

Yeah, it is a combination right? Certain points where you want to stop and think deeply about what you're trying to build and what's the right way to approach it when it comes for example to Two policies right and rules and enforcement policies. So we built built it quite simply saying okay We need to add a policy here. We need add ability to get over here agent agent communication network requests creating an agent a new agent Having adding new NPM packages into the agents environment those things we have approvals and we added more and then we got to this point where it's Okay, we've got eight different places where we have these approval flows that are being enforced by lines of code and all kinds of places project and There's a point where now we're working on how do we create enforcement of policies and rules as Enforced by the architecture and not enforced by a random line of code there and around the line of code here and That is I guess coming from a need like we look at it and we say okay.

There's a need here. We got to tackle that I think when it comes to the security side That's where we're being a lot more careful and thoughtful about things in general Yeah, it's build the smallest version So I you know we write our kind of what we're building You've got the P1 P2 P3 and you know kind of milestones And I find myself going to P0 and then I'm doing P0 0 and P0 0 0 and just scoping down like what is the absolute minimum thing? We could do here that's gonna work and then let's start adding on gradually as we go I think it comes from let's figure out if this is something we need it all but also it helps to focus the development It's so easy to write code now, right or send an agent off the right code So you can get a lot of a lot of code and and it just becomes bloat so scoping it down to the absolute minimum and kind of Crafting on little pieces that you need helps control the scope agents will just suggest Oh, why don't we add this? Why don't we add that let's add it?

You know defensive mechanism here and validation here, and I think as architects we have to keep them keep them focused You know it comes down to attention right human attention agent attention and pointing it in the right place But I think also it's about collecting requirements So build it get people using it and then figure out what do they actually really need and you think just using it yourself I have an agent build a prototype for you hacky dirty prototype in a half hour play around with it And then feel how you know, how does it work? Is this what I really want? So yeah, build the simplest thing generally as a general 100% what are your thoughts on creating an agent in terms of? Doesn't agent get and I know you need it Andy, right?

So it has an identity in terms of a name, but how much further beyond Andy is It may be for nana cloths one way and in your mind and how you feel about other agents is different But help me understand what you think about agent identity like what exactly is an agent identity should it get an SSH key? Should it have key like things? It could be its own thing should it when it commits to your repository? You know wherever there needs to be an audit of a log of who did it?

It can't be you know, you everywhere It's got to be probably like your sub agent Andy like how do you think about identity and what exactly mints an identity for you and nana Long I don't I think it's a little bit of an not fully solved problem. Yeah, okay Yeah, yeah, I think it goes back to that thing of how can we unlock some value do something with the primitives that we have? Knowing that we don't have all the pieces in place yet all the you know the cards haven't been and been turned over yet So I think what we can do now is Actions that require approval so actions that are sensitive need to be So what we have for example we have agents that are reviewing Reviewing code testing it and then making a suggestion of this this is good to merge right and then we as a team are looking over Their suggestions and this is an our slack is one of our agent factories for review code We look it over and it's got this command that is saying okay This could be merged so it writes out a command for us and then the agent can't actually run it doesn't have any credentials in its sandbox But it writes out the command and the orchestration part of nanoclaw we've customized so that it gets that command and shows us This car saying approve reject right and then we have in the credential vault each person in the teams credentials and the orchestration layer When someone clicks approve it looks at who clicked approve and then uses their credentials right and that's very intentional It's you have to go The agent can't merge code and we don't want our agent merging code It can do a review it can give us context and surface things and point our attention at here's what it's worth looking at And here's how you can know this is mergeable But in the end of the day were the people are the ones who are merging code and it's with our credentials It gets a bit more complicated when it comes to read read actions where you also need audit and logs In that case, I think you do need to have a human identity But delegated to an agent and I don't think we have the mechanism fully in place yet for that But there are some great companies and projects like one of the ones we partnered with which is called one CLI and they are building that Identity for for agents so that you can express those kinds of concepts Yeah That's interesting to make an approval and this is a nanoclaw thing This is like maybe your thoughts, but also I imagine most of your thought you're peaking into your ideas your DNA And you think about things are being baked into nanoclaw you said that agents don't merge code But they can do all the things that surface intent and you'll hear a bunch of other people say oh my gosh If I had to merge every you know if it's a pull request sure if it's a merge request sure whatever you want to call these things These days and sure it'll change soon because we could have going down and something else is coming up Not only like going down like negative. It's more like in terms of usage A lot of upset with you know man gosh.

It sounds like you want the human in your in this policy driven world that is inside a nanoclaw I understand correctly that you don't want an agent to merge the code you want a human to approve it and the merge is is Accredited to that person and their credential versus the agent who in quotes actually did the work is that right? Yeah, and I guess you could you could zoom out a bit and think about it on more of the abstract or philosophical level of the world that I want to see evolving and developing is one where humans are still at the center and stay at the center and agents are amplifiers and They amplify what humans can do so using agents humans can do Ten times a hundred times a thousand times. We're probably reaching a point where there are ten thousand X developers out there who are doing you know rewrites of of massive open source projects in in a matter of weeks and Building out you know successful projects and days, right and it's but we want it to be the person who's now ten thousand X and not just an agent that brings all this value but the humans should be at the center and and I Don't necessarily if we have to be like maybe you could build things in a way where we remove agents remove humans from this process and Companies just become a whole bunch of agents. That's not the world that I want to build I want to try to build things in a way that humans stay at the center.

We have our place we Are the ones who are giving the directions and making the important decisions and and saying control? So so that's the way we're building it when we're bringing it to companies It's the same approach We're saying we're gonna give each person your team an agent and assistant that's gonna help them help the person do their work gonna make them more effective to three times more effective and and the people in your team need to become Managers of agents like that's where the world is going if you've got 10,000 people in your organization fast forward two years You're gonna have a hundred thousand agents in your organization So every human has to become a manager agents and that's a big transition for people who have never done managerial work before they have to learn a lot of new skills like Clearly communicating what they want and what their intent is giving feedback Taking responsibility reviewing other other work of other people or in this case other agents So it's a whole new skill set and the way we're approaching it is the starting point is give each person an agent where it's one-to-one They take responsibility for it They give it feedback They kind of train it and tell it what they need and what they want And that's gonna get them started on this path where they're then gonna manage a second and a third and a fourth and a fifth And I think organizations that are able to do that process effectively There's gonna be a place and value like there all the people who are in the organization who have a lot of tribal knowledge and all this expertise That they built up over a long time There will be a place for them and they will be able to bring value fast forward You know a year or two years and they won't need to lay off you know 90% of their team because the people are gonna be able to come along with them into this value generation that agents are creating Organizations that aren't able to bring people along you know, they're gonna they end up doing mass layoffs So I think that the responsible You know ethical secure way of doing AI is along that path of thinking How do we bring everyone along with us and don't just focus on the the super users and the tenant 10,000 xers But make sure that the average person is is able to you know It has a place is able to bring value in the future I guess it makes sense too to that nanocle is not a developer tool to create more software It is more of a business focus tool to as you said before amplify humans output Which makes more sense because when you think about agents and loops on the developer I actually think about how's it make more software, right? But everybody else who is not a developers like Like what software like, you know, not really that but about six months ago. Maybe maybe eight months ago My wife I'll share a quick aside on this and go back into our real conversation But we were driving the car I think and I think I said to where I'm driving and I think I said to where I forget the exact conversation But the important point is that I was making a remark about Linux powering the internet and I said something like babe You know people have to know right that Linux is what powers the internet, right?

She's like no No one in the world besides people like you Adam know that Linux exists No one your average person who just doesn't know any about software or software development Maybe they've heard of it They have no idea what it is and the fact that it runs mostly internet large majority of it is is Lost on most people and I was like that's that can't be true That can't be true So she goes home and she hops on Facebook, which is the place you talk to most normal folks Facebook Instagram and She puts this post out and it's one of those banner posts It's like a it's got a I guess a banner image and a big text kind of thing It's not like this little text where it's her prose like a post might be it's more like an image And I think it says something like probing her her people her friend groups about this the subject and the comments were hilarious that This thing even exists that Linux exists like what there's something that powers the internet not not a hamster will with hamsters running the internet Like there's a bunch of jokes and so egg on my face I had no idea that the rest of the world didn't know that Linux runs the internet Okay, so that being said back to nanoclon and it's in its case the case is largely focused on amplifying business output So it makes sense, you know Some of the choices you've made and how you've made them because it's not a developer tool to make more software It's a different tool for people to use to amplify When you think about that like that kind of installation is Uniquely different maybe not uniquely different but potentially equally different than developer tooling is installed in enterprise I just installed in a call on Mac mini, you know, and I'm not worried about Business continuity. I'm not worried about the databases that it's making because these agent to agent conversations and this as you mentioned before one of several agents Now, you know Adam has four or five agents because I work, you know an accounting or whatever and the next year I have a hundred agents like that begins to become Like business critical, right? You think business continuity does that's recovery like these are all Phrases that come up in this world. How does nanocall fit into that world?

Take me through what it might be like to instantiate? Nanocall in an enterprise that you're consulting for and with to build out their agent fleets, etc. How does it work? Give me a give me a zoom into that world.

So the first thing is like you're saying it's business critical in some ways the agents become the whole company it's kind of their workforce and for any kind of large company that has to be in their cloud environment right in their AWS account or GCP or Azure and you know starting to speak to some companies now they're even on-prem and They don't want and they can't have any of their data other employee data customer data sensor data leaving their cloud environment So we do deployments fully into their cloud environment into AWS bedrock GCP with vertex or you know, you can deploy to Azure connecting integrating with their IDP octa on tra whatever they're on and It needs to be The continuity part I mean it is it is mission critical for the company. So I think The idea that this is going to be sending data externally or living externally, especially when you think about agents building up Knowledge and memory, right? So okay, you're sharing sensitive data with them But then it's not just a file that can be deleted that then gets added to all kinds of other files and and places where the agents stores information and You get the the ideas like you're saying of you know now everything that agent knows is sort of Contaminated with sensitive data. So the whole thing just has to be in the companies in the company's environment There's also an element of this is so complex that You can't expect companies to look at a super complicated architecture where certain things are running on their cloud and certain things are running hosted and certain things are running somewhere else and expect them to look at that and go Okay, this yeah, I get through this whole complicated architecture.

Why this actually is safe and secure. So everything running in their account There is a credential gateway Where when employees sign in through SSO to authenticate with Google or other? Services they use the credentials get stored in credential gateway agents run in Sandboxes all requests are proxy through the agent gateway and Are then less repolices are enforced and credentials are injected so the agent gateway hold secrets The credential gateway hold secrets it looks at each request and it forces policies of should a secret be injected here based on policy set Should this request be allowed through should we enforce human approval in that case send a message to the messaging app to the user asking for approval? And that gets sent just by the gateway without it going back to the agent and then there's the data I mean the way we're deploying it is Keep it really simple so we're not going and goes back to saying earlier not jumping to Kubernetes and and Thinking about you know, how do we scale this to a hundred thousand and a million agents?

Yeah, maybe we get there But for now, it's just really simple VMs, you know in the clouds been up easy to instance data is stored in EBS volume encrypted checkpointed backed up and Keep the architecture really simple. I think Just the last point on the architecture. I think people have maybe some wrong intuitions about what compute resources running agent workloads takes So they think always agents It's really heavy, you know all this inference and whatnot but your machine isn't running the inference right inference going to bedrock Even if you have your own open source models running in GPUs That's a separate GPU that's doing the inference. It's not just a machine that your agents are running on with their sandboxes So actually doesn't take much compute resources.

They're mostly doing some reading some files writing some files occasionally Mostly doing network requests for inference for tool calls a lot of time waiting for For the LLM So it's actually very compute non-compute intensive so you can run on a relatively small machine 16 CPUs 64 gig ram and I've tested this you can run 200 agents in each one of their own container and you set them off at the exact same instant Go and do something do a research job and then yeah And that's that's totally fine They can handle that and then if you think about staggering the starts So I have aged active agents, but they're not starting at the exact same moment You could probably get to 400 500 and then if you think about active users one machine small machine That's probably a thousand maybe a couple thousand users So a big machine in the cloud, you know take the biggest machine you can get standard on AWS You run tens and tens maybe a hundred thousand agents When you're thinking that they're not all active at the same time. Yeah, so I think people's intuition is a little bit off Latency also is a major issue when it comes to agents You don't need sandboxes. It's been up in you know 12 milliseconds or 32 milliseconds or whatever It's you anyways wait multiple seconds sometimes minutes for the agents to do their work So even an extra half a second or second of late doesn't matter. Yeah, really.

Yeah, it doesn't really matter. Yeah That's interesting. So how and everything you're doing is built on the open source version of nano cloud You have a separate repository that you deploy into enterprises or what's what's the take there separate or same? So it's the same nano cloud.

There are separate things that are not it's not a different version of nano Call is just separate pieces that you don't have in the open source things related to connecting with identity providers and audit logs and governance very enterprise things. Yeah, yeah, so there's very good Yeah, it's kind of a whole separate service So we pick up the nano cloud service Which is very much it was just the open source and then we raise the governance service and the two talk to each other But it is very much a separate service so it isn't like extending the open source and then the open source itself is the Nano cloud is the open source version We do need to customize it for different customers based on their needs and that comes back to the skills approach So we've really gone all in on this skills approach and we're building custom versions of nano cloud for customers So I guess it's important to say there are tens of thousands of users of nano cloud the project on github has been forked something like 13,000 times Many probably most people using it have their own fork So even if they have officially forked on github they've cloned it and then pointed it to their own private upstream the private repo So there's tens of thousands of forks of nano cloud and then each person is customizing it and It's a pain in the ass to pull in updates Right because upstream is changing and then you want to pull in and you've made all these changes go based then you get merge conflicts So we've said you know what if you want to maintain a fork and you want that fork to be maintainable over time and to be able to pull And updates we're gonna do all these things on our side to try to minimize the amount of changes and make sure we ship migrations and Keep it with change log that identifies breaking changes every breaking change even if it's not like Migration for the database it will come with some kind of migration for your project So saying maybe it's a skill maybe it's a little read me that explains what the change was and what you got to do to Maintain it in a result conflicts, but then also saying if you want to customize the code base and add all kinds of custom functionality Don't just go wild in the code base make Do modular maintainable changes what that means is add files right that add functionality and then have small integration points Where you kind of create your own little hook in the code where you're integrating But keep it a really small hook that's just two or three lines of importing function and then wiring it in one specific place So by keeping added files, but then for the upstream files. I keep really minimal integration surface that minimizes merge conflicts and then every New capability you want to add your project create a little skill that documents what you added and how you added it and create that skill Should also have with it tests that don't necessarily test the code of the capability But are just test the integration so like you want to write tests for your own code That's great But part of this or the contract if you want your fork to be maintainable have a test for every single integration point And it's gonna be some kind of sometimes a test or like proper tests that are kind of testing functionality end-to-end Sometimes if it's can't be tested end-to-end just have a test that like AST looks if something exists in the code so that if I pull an upstream changes and This thing gets wiped out by an upstream merge conflict I've got a test that's gonna go red and tell me hey that thing got removed and then I can rerun the recipe that explains that Sorry the skill explains how I customize it and then have one meta skill which were calling a recipe that Just list the different skills that are applied to the project and any kind of bigger picture things you did So that you now have Documentation of your fork and you've also did it in a way where you probably won't even need to go back to that documentation most of the time You can just pull in upstream changes if things go really bad and they break you can always go back to that documentation and And we're building yes So we're building all these customized versions of nano club not for enterprise in general but per customer But following those same principles so there are tens of thousands of forks out there We're maintaining dozens and we want to be maintaining hundreds and eventually maybe thousands of forks for different customers and that goes back to our factory There's certain processes you need to do to keep those forks up to date and to then be able to build them into images and push those images out to Customers accounts, so that's our agent factory. We're building to build software in this different way That's trying to be a bit more a I needed and leverage the full capabilities of agents.

That's interesting. What do you um, how do you keep it? I guess the easiest way to say is how do you keep it all together? But you got more than you building this you got more than you customizing this for enterprises.

You have a good philosophy and a good Process it seems but how the question mark here I suppose is the agent keeping that agent Focused on your architecture in how you described it. Hey, we're just paraphrasing We're here working on you know customer xyz custom in a claw. Here's how we do it How do you keep the agent from not like going back to traditional ways how do you keep them in your world in the way you govern things? And is that a problem especially when it leaves your desk or your workstation and it goes to an employees workstation Who's building on the claw for you or with you for a client like how do you keep everybody in the loop and do you?

Do you actually do it well? It's I think it's working pretty well so far some of it is is sharing context with people so communicating with people and and having Daily conversations about how to build things and why we're building what we're building Reviewing code. I'm looking at code. I know that's a bit taboo in in 2026, but like I look at code and talk sometimes about What you know a variable is named if it's something that's really important.

It's on a critical path and we know that that's gonna be a hot spot But I think for agents My perspective is we need to be spending a big portion of the time maybe it's 50% maybe it's even more of Setting up the right environment for the agent to be able to work effectively and that's not a one-time setup It's gonna continue a space so meaning rather than just pushing code pushing code pushing code Invest in the instructions in the context in the test suites in the lint in the hooks in all the things that keep the agent on that straighten our path and When it comes to a project when it comes to that philosophy of create the skills create the recipes It was an idea that bounced around my head for weeks and months and then eventually and it's not that long ago a month Month and a half ago. I said, you know, we're gonna go down this path of building for our customers the same way the community is building So we're really like tying our destiny in with the community and if this project isn't working for them It's not gonna work for us and if it's working for them, it's gonna work for us and Part of that process was saying okay I have this idea of how you can customize in a way that isn't gonna be a pain in the ass to keep updating and we're gonna try to do that ourselves and let me write this this up properly and commit it to the code base and push it out there and Link to it reference it in the cloud. Indeed. It's committed with the project So that everybody else is aligned on how to do this and hopefully they start to build in the same way And that I think of it almost as like a contract between us as the maintainers of the project and the community saying here's how we're gonna be doing things going forward and we're gonna make try to make this work and if you guys want to Have some level of commitment from our side to to not breaking your fork Then you're gonna follow you know the this set of things But it's kind of mutual responsibility you guys follow this side will do our part to make sure we're developing the same way And it seems to be working so far Check back in like six months.

Yeah, right. Well, that's cool. So I mean it's it's it's burgeoning this new movement of Skills recipes contribution. That's not the way I was for a source You said that before that if you're gonna contribute contribute a skill not code But this idea of having many forks customize versions of nanoclave or enterprise or building for You know as you're saying that I was just thinking to myself Okay, so you're you're tethered to the open source version the community uses and if it's not working for them It's not working for you or it you know that there's a symbiosis there.

It's happening. What's kind of interesting Yeah, I do think about going back to the open source model I'm trying to think about it in a way where I don't want it to be an extractive relationship like there's two entities here There's a project and it is you know legally owned by by our company Nanoco, but it is its own thing It has a community and it's got a user base and it's got its own identity And that's a separate thing that stands kind of on its own separate from the company And then I want the relationship between two of them to be a symbiotic mutually beneficial relationship And I don't want the company and trying intentionally to not build a company in a way where it's extractive and kind of mining this community and the Project for for the value that that's in it But instead building its own value but in a way that as the open source project succeeds and the community grows That benefits nano code the company by you know people knowing about it name recognition validation Driving people who who then say hey, can you guys help me set this up for my company? So that kind of inbound Funnel and then on the other side as nano co succeeds and we continue to build our team and develop We're gonna be able to build the project better and maintain it better over time And I think the best open source projects in in the long run I wouldn't say best there's there are great small projects but projects that have have made a real impact have longevity have big user bases That continue to succeed in flourish in the long term. They do seem to be connected to a very successful commercial Business that that is funding it and maintaining it.

Yeah, I mean because you got to fund the future of it And you're not taking code contributions right like do you not is it a role a policy? Like we do not take code contributions It isn't really a hard rule. It was kind of worded that way when I initially launched it It was also like 40 hours of coding. It was late on something right.

I was I was feeling kind almost like Everybody yeah, I was like get off of my lawn. This is my agent. It said in the read me. I was like You know it runs you can run it, but like don't run it as is that be weird It's like this is my agent don't don't use my agent like for it do something that different but um That's kind of what it said in the beginning It said no code contributions just skills and like okay bug fixes if you see security issue But no no actual source go changes now.

It's become a little bit looser because there are improvements to code base that benefit everyone that make it more Maintainable more robust not everything is about fix sometimes its added capabilities. I have this kind of this kind of little equation, which is like lines it's It's functionality right so when I'm looking at a contribution the functionality that it adds times like the target market is a super niche or Or I would say not functionality of utility times like target market how broad it is Divided by lines of code. So and that's got to be maximized So if you're making a really small, you know change and it's bringing a lot of utility for a lot of people That's awesome And then you got to play around with those and try to make sure that you're not adding like 500 lines of code to handle Some even if it's like it's a bug right and you found it and you identified and reported it and it's reproducible But if this bug takes 500 lines of code to fix and it's affecting like a tiny like you're three with three other people We're not gonna merge into code base and just fix it on your own fork and the other three people can also fix it on their forks Well friends I'm here with the CTO of build kite and one of the most challenging problems of modern era software development is Continguous integration and continuous delivery and so locklin Donald build kite CTO What do you think about today's teams the challenges they face the speeds at which they're developing new features new code? It is just overwhelming.

How do you all think about that such a good question is the question everyone's asking right now? All of our big customers are asking us at the minute like you know if we five or ten X That's where we put this year or a thousand exit what breaks and when and you know My answer is kind of same as it's been for the past 20 years Which is the bottleneck is still trying to integrate those code changes in and then deploy them and check They work and then keep them working as you keep throwing more and more code at it I think a lot of the fundamentals are the same But we're just a thousand Xing the speed of it and you know that changes nearly every variable. Yeah for sure Okay, so where where does build kite thrive? What particular type of team or enterprise do you thrive in the area that build kite has always thrived in is like this like fastest moving tech companies of the Well, it's like we've been disproportionately successful in that small niche that kind of Shopify class uber class, you know Open AI class of folks that have this key problem around iterating really really fast And you know the thing about all those faces they all have subtly different needs subtly different problems And so we've tended historically towards building like really well engineered lego blocks that scale like orders of magnitude more than What our nearest competitor does so you know I think that that puts our system in this tension where you know You've got to spend some time assembling those building blocks that those lego blocks to get the thing that you want But the end results is far and away more performant and scalable and the experience is better than what you get from something that's off the shelf So I think we've started from a position of really well engineered lego blocks And then are kind of working backwards towards kind of creating the thing that scales down to a startup that starts with one person and ten agents next week My friends go to build kite.com.

That's build kite.com You deserve better CI engineer for the frontier. We are all facing trusted by the teams setting the pace again build kite.com Once again build kite.com We'll stop someone from nano coing you It's open source great idea This is all amazing. Let me just copy not so much your company But copy your idea around a company to build above the layer of of of nano claw like that's open right anybody can do that Right that doesn't change anything. How would you feel about that?

You're like hey? This is my lane nano goes our thing We got funding we got a mission. We got employees. We got businesses to serve but you know can someone else Put someone else build their own services company just like you the senior base They can I feel really good about our position competing against a company that decides to just go take nano Co nano claw and go directly down our lane because you know we and it comes back to the brand like we are Nano claw right we're the company that created it where the company that built a maintain that we're the people who are building a Maintaining it and the legitimacy the credibility the trust that you can't just fork that right so That that I think is what we gain and it's not something that we extract But it is something that we gain from the open source project the trust that I think that's huge now when people realize how central agents are becoming They're looking at each one of the companies that are providing AI models and agents and we're not in going do we trust them in the long term?

like deeply and So I think that's super important the community that's built the minister for an affairs of Singapore using it and under kapathy kind of tweeting excitedly about it that creates a lot of validation a lot of trust and then also we are we are Building a team of real experts in building agents So the people who are joining the team the AI engineers that are joining the team these have tended to be the people at a company Who are like the number one person who's like pushing for AI adoption in their company? And they're doing the webinars and the sessions with everybody in the teams and the workshops about like you know you got to move off of Co-pilot and like it's now you know Clucko is a thing and you got to start using hooks and you got to start using that and they're like up to date and they're posting about it on X and other places so that person in the company who then feels like the company is a moving fast enough for them Those are the people who have joined our team and we're building out this whole team of those people So I think people can compete and you know I'd recommend not I'd say try to pick a bit of a different lane on top of the nano club But I feel like we have a really good position We had a head start and I think we still have a really good position But in the end of the day we have to move really fast execute really well in order to continue to Continue to succeed. I'm really motivated to succeed because I think beyond just like oh, we've got great agents and they could automate work Really well, I think you know the approach and philosophy of keeping humans in the center Isn't I don't think necessarily that things have to turn out that way? I just want them to so I want to I want to succeed for that reason to make sure that we advance the way that we you know We think AI should a should look in the world and work In the coming years.

Yeah, that question not even as an adversarial question, you know like someone could Be inspired and there's only so much businesses that you can actually take on right like you got a finite amount of people to this point There's a certain on a bandwidth you can actually control as nano co And the reason why I ask that question is like even me like I I've got people because of who I am and what I do and what I know Asking me to help them right and I've started a small consultancy. Let's just say and it's really people. I know It's not like I'm trying to advertise I'm not advocating people to reach out to me to ask me to solve their problems It's literally friends of friends that I know personally They're a neighbor or I know their business or I'm a patron already or whatever it might be where I see they have a problem I care about them as an individual human like an individual person in my community And so that's sort of my my litmus on that and so the reason I ask is like I Know at least two people that want my help is gonna be like Adam Can you help me put nano claw my business and I'm not gonna turn into nano co, right? I'm not gonna stop on your on your lawn by any means But I'm gonna start growing similar grass right potentially in my quest to help these folks isn't my mean business I'm trying to build a capitalized, you know services company No, I'm probably more than that open source market where I want to leverage the twee put out their free open source for the world to use MIT license for all the reasons you did it and do the same thing you're doing with it But not at scale, you know And so that that's my aspect questions because you got more and more people maybe even more people in the in the In the club world there are users making their own agents using it themselves that people are saying Hey, can you give me what you got?

Are they gonna send them to nano co because they're a company probably not maybe but unlikely and you get in this kind of really weird world I something even telling you about this like this total remix like I know the fork idea was invented in 2009 or 2008 when GitHub created itself And the idea of forking a code base was a brand new invention Almost 20 years ago now like 18 plus years ago now But here we are talking about you putting out a project used by tens of thousands folks with humans at the center MIT the most promissively way the license and opens for project you're putting a company on it and you're advocating for essentially And you're doing it your for your own project for the benefit of the customers are serving the client reserving So like we're in this really where we're like everything literally now is a remix in some way shape or form Right, you're talking about upstream versus downstream and even me asking you about this potentially non adversarial approach to how can I actually add benefit to the nano Claw world by helping my my my neighbors essentially like not 20 not 30 not 50 more like three or four, you know I'm helping out. How do you feel about that? How do you feel about the fact that that's now reality because a while back You spent 40 hours straight going blind producing code to turn into nano claw. I feel great about that I it makes me happy every time I hear about someone using nano claw building a business on it providing value getting value out of it I think like I said earlier, there is so much value just sitting there heaps and heaps and piles of value And when I see someone picking some of it up, I don't feel like they're taking it for me I feel like there's just so much out there and we're all creating value and I created a project in that created a lot of value But you're setting up a company that project you're then creating even more value and I set up five companies and I've created more We're focused on Fortune 500 fortune 1000 large corporations.

They have very specific needs. I think we're really well positioned to provide this for them and We're we're providing services, but you know, I started building an AI native marketing agency So the whole idea is provide what would traditionally be a service, but then do it in a way that's scalable and where you can Where you can use agents automate certain parts of the process. So that's the approach that we're doing with nano co as well I don't see it as necessarily a service company. I think everything's kind of blurred now.

Everything's remixed So it's not necessarily services or I would say product company. It's an AI native company. The model is Deploy agents in a way that looks like a normal service But then continue to maintain over time and charge a monthly subscription for for the agents I Think in the longer term I'd love for you to for so for you to do deployments with nano claw. That's awesome I would love to just on a personal level, you know give advice helping any way that I can I think it's a company I Think you'll manage but but I'd love to just also just hear about it get feedback from you get input I think if you do deployments with nano claw the community is now stronger because you're you know Really serious person.

You know your stuff and you're gonna see some issues. You're gonna push back some bug fixes You're gonna send me a message, you know a message at like 3 a.m. Going like hey do this thing isn't working and you know You're gonna request different capabilities and features So that's gonna make the community stronger the more people who have built real businesses and real services top of it The more I know this is a community that's gonna survive and it's gonna continue to continue to grow and there's more people in here It's not just us with our you know 12 million seed funding trying to push this community up a hill But there's many many other people in it involved building creating and maintaining invested in it and then I Think that over time We're gonna get more and more requests from people who are building on top of nano claw around nano claw under nano claw You know using nano claw we're gonna get those requests from them to provide some sort of support for them in different ways And at some point we'll probably do that it's not the focus at the moment But when that poll becomes strong enough where we just feel like this is needed will do it I think that the first step there will probably be Bringing nano claw to a specific industry. So what you're talking about but people who are focused on one vertical so they're doing it for the construction industry or for you know retail and That would be people who know that industry really well So they're really well positioned to build out the agents and the skills and the instructions The connectors they know all the different tools and how to use them that you know the retail industry uses And they will they're really well positioned they also have the network already in that space and they're connected to a lot of companies They're really well positioned to sell to those companies to support them to do the Go through the process with the company of figuring out what exactly their needs are But then they probably don't want to build their own factory to maintain a whole bunch of these deployments So I think the model will be they make the sale they sell to the company will provide to them an easy way to do these deployments and maintain it over time Where it's kind of like a multi-tenant type of setup where we can give them access as a partner and they can do really simple deployments for their customers and they probably earn a lot on the front end of the setup fees and then Continue to get a share in the long term of the fees for managing and there probably won't be much work on their side for Continuing to do a little bit support management here and there for like hey my agent You know retail assistant it got really dumb and is forgetting things and they'll go in play the agent doctor and like help You know figure it out and fix it up But the more infrastructure type of maintenance will be able to do for them this whole conversation has got me thinking especially talk about agent factories and The nature of this towards business is like I'm not really sure how to phrase it But just kind of where I'm camping on it.

So you know energy my idea here is the Linux of Is something of like Linux Linux Torolds back in the day was like you know what I'm gonna put this out there That was a big of open source essentially at least some of the earliest days of open source and You know people are like wow would you put that there for free and if I could use it? Well for the same reasons that you embody which is like I want the world to use it. I want the world to get benefit from it I don't care remixes it I'm remix it myself and you know That's largely kind of how Linux became Linux and now we have slews and slews of distributions and the fact that Linux exists And then a clock and exists because you're built on containers Linux containers You know you may on a Mac install Docker, but that Docker containers running some version of a Linux distribution Could be op-in on what you've chosen to go into the lines of code you can share here But you know you've chosen Linux and Linux containers because you can spawn those easily and like thankfully I don't know if this news is a big W or not and maybe it changes for you is Apple containers and the container Command line tool that's not available on any given you know M series Apple Silicon Mac Which I think is just amazing it's like WSL for Windows is now come to Apple and come to Mac OS And I tell you what like like the audience may see me there on YouTube But they can't see me man like I am smiling about that right the fact that we now have sure we've always had Linux containers via Docker But Docker has had some checkered past with rug polling licensing sure they're there they're a for profit company I get it you got to make money nothing against them whatsoever With that but they've had some checkered past and having Apple support containers natively has got to be exciting So I'll get off my soapbox to say that I'm really curious what you think about the Linux of is you got open claw You've got nano claw and maybe they're both claws but not the same claw. They're cut from similar cloths Gosh, so many puns here.

I'm sorry about that How do you feel about this idea of like is nano claw the Linux of agents for business? Like have you put some thought into that? How do you feel about Apple containers? How do you feel about being built on Linux?

Take us into that. I thought I'll start with with Docker. I love Docker They are invest they have invested in nano go so they're in our secret. I'm so full disclosure.

I know that Yeah, so we have you're not here for them. Yeah, I think fan of Docker and especially we've been recently with their sandboxes Which you know they're building for running agents or whatnot, right? So Yeah, the you know what we got great investors to see around for sale invested a Docker hugging face SEO climb he's part of the round so Docker you know initially what's funny is that Nano claw actually ran initially on Apple containers. So when I launched a product project It was what's at baked in and Apple containers baked in just because I bought a Mac mini and I had Mac book And I had been meaning to check check out Apple containers and then I was like I'm building this any containers Let's give it try and I launched it knowing that most people probably won't Docker containers But in the read me part of the angry notes and the read me was also like it runs on Apple containers Why because I thought it'd be cool You know what about supporting Docker containers?

It was like just fork it and change it to Docker containers and you know I won't accept the contribution of supporting Docker containers alongside so it was very like but the thing was after You know a few weeks there were thousands and thousands of people using it and everybody's Most people are changing it from Apple containers to Docker containers and there was a certain point where I had to say okay This isn't my personal project anymore. This is actually there's a community here and I need to be a bit more You know responsible and you know to that and the default of the de facto container is Docker containers It's what everybody uses everybody's run for many years works everywhere So I moved it over to Docker containers. They're now building dr. Sandboxes that got a governance Great product there and were integrated with their sandbox as well, which is like a micro VM with containers inside So and yeah, I didn't have to I don't have like a contractual application to promote them But I do like them in terms of the Linux.

Yeah, I totally see it. So my my brother-in-law is actually a rabbi and he Has a group of rabbis that are They had their own fork of nano claw and they changed the logo from a lobster to Some other animal because lobsters aren't kosher and part of their fork their distro of nano claw is that it doesn't like you do schedule tasks That run you know every day a certain time so it runs those tasks But then it won't run them between Friday night and Saturday night because that's the the Jewish Shabbat where people don't work So that's like kind of like Sunday when people go to church So they created their own flavor of of nano claw the only reason why I know about that fork is because that's it my brother What happens to me and he didn't create it right? So there's probably hundreds maybe you know, maybe more of these forks So there's a little tiny community that's gathered around the fork and is building their own flavor of Nano claw and I so I totally see it Linux for sure Yeah, and that I think is the future of one of the pieces of future of open source projects where it becomes Distributed so it isn't just one project It's you know a whole bunch of forks and each one can have their own community and if you do it right Hopefully the forks can benefit the upstream main project and main project can push updates out to the forks as well That's really well Yeah, cuz I mean, you know, this is your world more than I mean, it's our world But this is really like your world where you're building an agent factory. I'm using agents to build a factory I'm not building an agent factory I think most of us are any of us who are building software sort of like building software to build software better Which is the whole AI changes everything we talked about before and AI native so you start to question Okay, why can't use this because my agent has challenged with it or this isn't really agent friendly This can be far more simple whatever for any of the reasons.

Do you feel like? You know in the claw world. Do you feel? Do you feel like open claw is is the Linux of agents?

Do you feel like nano claw could be the Linux of agents like what are your feels on? Smaller than open claw obviously and maybe I'm wrong But I think you probably are in terms of like especially lines of code You're super small compared in comparison But you're kind of like not laser focused on the same user base the same trajectory while doing very similar things and being conflated Just by the nature of using the word claw, right? You chose these were claw because there was some brand equity to leverage there How do you how do you feel about open claw nano claw Linux of well? Is it a winner takes all kind of thing or is it you're all just flavors of the claw?

I think it's pretty Conclusive now that it's it's not winner take all if you look at for example Hermes. Yeah that project now has like 200,000 stars They're massively successful. I think if you want, you know, evolving agents. It's changing all the time great project If you want an agent that just is a bit more stable reliable.

I think nano close a bit better in that front open claw You know, we all kind of owe the whole claw community We owe you know a debt of gratitude towards open claw and Peter who created it because you know was it did show what was possible I think you know, it isn't my kind of value system Wouldn't allow me to create a project in that way of just putting aside initially security and safety concerns and just you know Going wild with let's connect everything and see what happens But maybe it did require that in order to get to that point right like maybe someone had to go and say Okay, we're gonna put all the security safety software quality put all that on the side Let's just see what we can do and maybe that's part of kind of how you build now with AI For me that my my value system wouldn't you know wouldn't allow me to do that I had to think about how do I do this safely? How do I do this in a secure way? But I think There's definitely space for many I think for businesses I think nano close really well positioned to be to be the solution and There's space for a lot of companies to take claws to businesses and to build all kinds of products on top We're positioned really well to take it for to the largest companies and you know I with all those sort of philosophical you know stuff about About wanting to share and let everybody build on it and all that in the end of the day I'm not you know building a nonprofit and building it we're trying to build a very you know large successful company Relatively small so so that's sort of the nano company. It's like an AI native company That's you know small for for what it's doing, but an absolute terms.

I think we're gonna have to grow and and Yeah, just you know to close the loop on the open claw and kind of the inspiration from it So I looked at the code base initially of open claw I'd seen some security issues when I was setting it up and I thought okay, you know, it's cool. I get the value I want to I want to build something that gives me that same value without the security issues And then I went and looked at the code base And I saw how big it was and how messy it was and I was like this I I'm not gonna spend now days and days trying to sift through this code base and understand that and figure out how it works And I don't think anybody really understands it and has sifted through it. It knows how it works It's just kind of this organic wild thing that's evolved super quickly and you know became 500,000 lines of code within a matter of weeks So I said, you know what I'm gonna start from scratch and just start with with a coding agent right with cloud code and Prototyping with it and iterating and brainstorming and architecting together and just start from a set of capabilities This is what I want and this is January. So Claude's knowledge caught off in January was like maybe June or July 2025 So pre open claw so it means that Claude didn't know Claude code that I was coding with my coding partner didn't know that open claw existed When when we're coding and I didn't tell it existed.

I didn't say there's this project called open claw And I'm trying to build a new version of it. I just said I want to connect this thing to my messaging app I want to have scheduled tasks I want to have a persistent session I want to run and critically I want to run any containers rather than just running it, you know bare metal and My Claude code in that code extension didn't know that open claw existed It was just starting from a blank slate and so built it bit by bit It was like 500 lines of code to you know before adding containerization and then with containerization It's like 2000 lines of code today It's quite a bit bigger with all the approval policies and a lot of the other capabilities it also we support now codecs and open code and You can run it with llama and local models and whatnot but and it now support like 15 20 maybe messaging apps So slack teams discord Telegram you name it but everything's kind of modular but Yeah, it evolved quite organically and it's you know become its own thing and and claw has become a category and you know I'm happy to be part of that category. Yeah, even as you're describing that category Because I'm not as steep as you are in the you know This called as that and that cloud is this you use an in a call in these ways and you would use open call in those ways You know or if you want this and you would use that I feel like it needs to be like a claw matrix of sorts You know that would just be helpful to anybody like if claw is the Agent OS the Linux of agents. Let's just say like the claw right and you're a flavor Let's just a clause Linux, you know in a in a comparison here and Nanoclaw is like a Ubuntu and or maybe open-clause Like Ubuntu and then the clause more like I don't know a different flavor here I'm trying to like I use like three Linux's maybe four I know I'm all but like I'm familiar with Debian Ubuntu fedora others I'm trying to like do a great job here I'm not obviously but that's pretty interesting to me is like is that the claw is kind of like synonymous with Linux and the various Distros nano open Hermes while it's not a Hermes claw.

It's it was what is Hermes is it? It's a god. It's a god in like a Greek god, right? You've all kind of like operate around this claw movement and created flavors and distros that fit certain needs Like you would use dead be in it if you got this desire and if you really want to torch yourself You know you would use nix or something else, you know If you really want to go to the like the uber Linux nerd way like I don't install packages I can buy packages Whatever might be right.

Yeah, I mean like that's kind of interesting to think about and I think the claw movement is very much So the Linux for agents. Yeah, so I mean I guess so we haven't shipped a binary. Yeah, so we're just it's just everybody's running it From source. So maybe we are I don't know me where the next yeah, maybe so I mean the initiative binary can't I suppose your type scripts and bun right so you could ship a binary right?

Well, it so it depends the orchestration layer is type script not bun is just type script, okay? But the what runs in the container so the agents environment is type script on yeah So it's kind of two it's kind of two separate runtimes is two two projects kind of we at some point We probably need to split it up more cleanly is like mono repo with two separate projects But yeah, there's the the orchestration layer handles routing of messages and spinning up and down the containers because they're not all up At the same you know all the time they kind of spin up and then they decide I'll go down handling the approvals handling scheduled jobs and all that that's all in that orchestration layer and then the agents environment It's just like the agent running in their messages being pushed into it and they talk to each other through these two databases where orchestration layer pushes information into SQL like databases pushes messages in and then the agent in its retirement has a polling loop and pulls messages and into the agent so yeah, so it's it's I think yeah, I don't know where I was going with that But I suppose even SQL light to doesn't really have permissions So you don't have to worry about like an ORM or access right you just open a file and read it right and so for two different systems To you don't really want both the right to it that would be kind of bad You can certainly wall it, but it still has some challenge with the rights So you probably should have one writer and one reader which is what you're seeing, you know The agent orchestration part of it is reading and while the orchestrator that's doing all the Linux containers is writing to the database That doesn't make sense. So it's actually yeah, it's exactly reverse It's two it's two databases for that. Okay, so it's each agent session has two databases So the one the host the orchestration part is writing and the agent is reading and the second one the agent is writing and the Orchestration is reading and Yeah, it uses a wall journal with like timeout and you know, it's it's complicated because you know the agents running in containers so these are totally separate processes and normal normal mode of regret doesn't work and and You know I had when I was trying out that mechanism because initially when I built nano claw Cues and there was like a queue for messages coming in and then a queue inside the container and a queue for tasks And it just got really complicated to do anything and then I Thought about this this thing of like what if we had this one shared database and then that's kind of all the cues It's just the one database like a message comes and I stick in that database and then the agent pulls from there and that's just everybody's one place and then Actually did a lot of profiling of running lots of reads and writes and stress testing and trying out all the different in ways of it working and then Settled on two databases one writer one reader and stress tested that and verified that you could get to like insane, you know Ten thousand whatever operations and you know bursts and whatever and it you don't you don't get corruption But with all the other modes that I tried you get you get corruptions at some frequency where it's just yeah Well the beautiful thing is you've chosen again back to simplicity, right?

You chose esco like you know That you couldn't get more simple than esco light and you resisted probably Vectorization at database like p2 vector or postgres or my sequel you just avoided all that I feel like almost everything I'm building Is still running esco light like there hasn't been a reason to go to a real database And I see that with a tongue-in-cheek smirk on my face because it's gonna is awesome Have you been considered and we're getting close on on time. I'm not we're into some technical bits. I'm curious Have you considered Turd so and the reasons why they've decided to rewrite Esquilite in rust are you feeling with terso is a snootie or you have you had to do to me so yeah, tell me about it It says a rewrite of rust. Let me see terso Okay, terso.tech what is terso?

Terso is an open source esquilite compatible database written in rust It lets developers create millions of small file-based databases for AI agents multi-tenant SAS applications and edge workloads so a lot of what That I'm familiar with glauber Is the CEO there for for terse me fed him on the podcast before? a lot the biggest challenge I think that they pose with betting on and leaning on Esquilite and if I and I could be wrong this is about in your back this conversation I'm even paraphrase my memory was that you couldn't call esquilite truly Gosh, let me get mad at this truly open source because the tests aren't open source and this is like the biggest issue with open source like Every you know CVE has to be open every this or that has to be in the open I say no to that right I think open source and we're kind of getting back to something potentially in the philosophy here is that I'm giving you an artifact a product you can use freely This is mean that you get access to the back channels doesn't mean you can access this that so I could be disagreeing with her So on these fronts here, but and maybe I'm even wrong with where their initial inception came from but they wanted to they wanted to make it faster They wanted to write it in rust. They want to leverage the SQLite kind of needs and be compatible And I'm so due for a refresh with glauber on on on Terson why they made it but this is sort of been in my back pocket as I'm similar to you a very happy Escalite user I'm not trying to make my database even more complex Because I'm trying to keep things simple until they have to be complex and while torso is adjacent to that simplicity It is open source. It is SQLite compatible, but it is not SQLite now They have lib SQL which is like the lower level rest primitive that they built Terso on top of and they have a funding and a cloud and so they have their own inertia But I have yet to convince an agent that and I have like you I'm tantalized by the tech out there and I'm like I kind of just want to play with torso Please agent we just say yes this one time to allow us to go off the beaten SQLite path and try terso and So far crickets they don't want to do it.

They're like not man. That's stupid like so. I don't know Yeah, I wonder if you know we're just everything's just gonna become rust when it comes to agents There's the you know bun is now. Well, I think they released version or about to release and I know there's rewrites of chrome and rust and You know, I'll check out terso.

I mean I think with agents I think there's the I try to let them stay on their on their in their lane on the path they want to be on I've spent like six months deleting these ridiculous comments that agents were putting in the code and then at some point I just said, you know what if you guys forget weird comments put weird comments like right maybe it does something for you I don't know right, you know, so I stopped For sure right yeah on the right on the initial inference and then the even timing I think about that is like it's less about The messiness and more about why you just wasted an extra minute on this turn and way more tokens than necessary to put comments I don't care about maybe you care about them, but whatever Yeah, but it's like our then we have to waste cycles in our rain cycles deleting them and and and fighting them consistently to keep deleting them and then I just give up I mean to and I think you know Maybe they know something like maybe it helps them when they're coming back to that code gives them a bit of context It's some sprinkles man like I don't know what they're commenting in your mind. They're commenting governance They're commenting spec 0 0 0 1 or spec 0 0 2 0 for example like that's the one that governs this function for example or This is actually from you know bug 0 0 0 1 or whatever number bug is in there So I'm kind of revealing some implementation details into my frameworks But but it's called agent flow and agent flow is how I build everything and it governs all my governing and without agent flow I'd be lost my projects. We lost every project uses agent flow agent flows become a hive mind. It's absolutely insane But it's all about coordination and stuff like that So my comments tend to be not like oh, I like this and here's some random agent thought and it's more like I'm putting this here because this reference goes back to the spec that governs this piece of code or we hit this issue and it Cause this code review which caused this bug report which caused this pep this project in his proposal That's governed by this spec, you know for example And so you kind of have this trail of issue bug code review agent work pep governing spec, right?

This whole sort of audit drove why does this exist? Which is the hardest thing for for people to you know in the vibe code world right is to like scrutinize Why does this code exist because I was crazy three months ago? I spent 40 hours on a weekend or on a Friday on my couch To the opposite of that which is well spec governed it pep implemented it and there was a bug report against it and the code review from two agents And then a pull request so all this trail we use back to Intent it leaves back to context and so an agent picks up later on I'm like totally not where I'm at if I have access to all that world They just painted in this comment well now I get to heck a lot easier to grok why this code exists and for me to delete it easily or augment it Because our future has changed whatever it may be so I feel like yeah Same thing with the unlike comment away whatever I don't care anymore Do what you got to do just make it awesome That's right. Agent flow sounds awesome and you know people people want agent flow so I think we got there and We'll have to talk.

We'll have to talk. I need I need some I need some help I need some help on I need a friend. I'm just do that. I'm just do it.

It's about packaging That's probably the one I'm so close to I'll have to circle back with you because there's so much you're doing with nano nano Clovid I'm just in amorbi and We're in similar worlds like if you put agent flow on top of you know, I'm not sure if you'd call it harness or not But maybe Something right If you put agent flow into Nanoclaw like the world would just sing you know actually if you put agent flow most things it would just say but it's largely Appinited largely focus on software development in a clause not focus on software development You know could agent flow fit anywhere actually it could but I think a lot of it is kind of geared towards and governed towards software development So maybe I can pull back a layer and make a little bit more a little less focused on software only because it's really a way of Thinking for me. I couldn't imagine running software without it. Like I would be Personally till you lost like the very first thing that me and agent do is we do research and that entire research project is documented It's not authoritative. It's not governing.

It's all ideas. It's all possibility. It's all what's out there It's not prescriptive. It's descriptive.

What does the world look like? What is the world? We're trying to build and it's all questions and answers But not this is what we're doing It's this is what we could do and so that is an artifact that gives me a chance to explore and unfettered and drop every Transcript from me an agent or an agent agent into there For it to then take and say okay from this source of facts not truth of our software What is our extraction from that that makes this feature that feature or the blanket statement for why this piece of coach exists or this Offer should exist like that if I didn't have that to operate from I really wouldn't know how to do it It all comes from the way I think you know the way I think about how I even jut down ideas It's like that like agent flow is very much a manifestation of how I think and so it's like Adam's brain as an operating system Great. So it sounds awesome.

Yeah, that sounds awesome So I mean and it matches how we're doing software development now, which is anything that's in any way interesting It starts with an exploration phase where you ask the questions about you know, what are the different? What's going on here? What are the questions that need to be answered and what are the places where decisions need to be made and what are the choices that could be made? What are the trade-offs?

What are the different possible paths and you go through that whole exploration and then we create an artifact which you know an HTML an artifact that has diagrams and visualizations and takes it in tries to you know not like a Eight-page thing necessarily but try to make it pretty condensed but just surface, you know put into attention the parts that are worth having attention Put on them, which is the decision points or the key decision points And you know what you need to know about this and then we share it with the team and you know It gets people to look at it and chat about it and then you go off and you know And that's that's really the that's really the whole thing after that you just send off an agent to go and build what you decided together And you see built yeah, that's I think the core of the architects working on yeah Leaving things stuck in chat or telegram or whatever like that's not where that should live that's ephemeral That should be you should you should feel unencumbered to have a deep conversation But knowing that you have a system behind you that extracts all the good stuff into the system that allows you to create artifacts that share It can be shared with an agent. It can be sure with co-workers. It can be shared with the client It could be shared with whomever really makes the most sense but like having that I guess you know that conversation and you said something earlier too with with the psychological change of going from terminal and Especially developers this like non developers won't get this but going from a terminal to a chat app of sorts You feel like you're literally talking to something versus trying to command the world like we've we've all been developers when I'm in the command line I am making I am I am I don't know doing things that are different than like talking to a human or Talking to something it's not a talking. It's a it's an action You're you're sort of like making things happen It's a whole different scenario there But if everything is locked in chat and you don't have this artifact system that actually has a system that connects to each other That has governance that has that's much policy But but taste and sense then you know your stuff is just stuck in chat That's not where it's meant to be but we have agents want agents for every new human and you got so many humans doing work Gosh, you got to find a system to get out of that to then create a memory system and all these other things like that's to me I think is um is where I'm most What's the right way to say like the most excited I suppose and that's probably not the best word is I'm just so excited about what's possible There because you take this corpus You take 17 20 30 50 revolutions of that.

Let's do research Let's create that hn artifact in your world Let's go then show that with people you do that over years even and you've got this corpus of information that now is Is such an interesting substrate for the knowledge base of an organization? Which is why like when you deploy nano claw you've got to be pretty particular about it because as this database grows I don't know if you're keeping one escalate database in prod or not But you got to have some sort of plan right and you got so much growing and so much they can extract from that that it's a This this a need of moral worry and marching towards and running towards in lots of cases. It's really interesting 100% I mean I think a lot of people talk about their Main assistant as you know the second brain and just builds up this information It's you know the LL M wiki patterns every bit of information you feed it goes into this type of Wikipedia You know you share with it some brain dump and it creates a Wikipedia article what you share with links to other articles that are relevant And then over time it builds up this you know all these articles and interconnected articles and it becomes this kind of graph But it's really good think of it as a Wikipedia of you and your projects and your world and your relationships and people work with and that's These this sort of second brain that knows what you know and knows your context and then in a company you end up with you know Many of those second brains each person in the company's got that second brain with all their information in context And then you get the company's brain which is this centralized place that some of these agents are able to push updates to and and and gather sort of the more general information that everybody needs to know and I mean it's super interesting you know we've seen someone who went on took took a leave took a turn to leave and gave their agent to someone else to Continue their project and it just like a project that would have had this whole period of offboarding and onboarding It was just right zero down downtime just full continuity. Yeah I'm really interested in that and like Just being able to have to swap out even a model.

Let's just say I've hit my fable 5 limit. Oh my gosh my world's collapsed No While codecs 5 5 or as of today 5.6 may not be quite fable 5 at least I'm not down and my context isn't trapped in fable 5 That was my reasoning maybe even my higher powered reasoning But swap the model out the context is still there the mission still continues nothing really changes Because when even with even the Chinese dress spent a lot of time like with anxiety Like oh my gosh like my stuff is all stuck in these chat threads that gets impacted that gets erased and like oh my That's why I got into this like I've got extract everything But that was too much but I'm really interested in that world where we can be where you can send Sally on vacation happily She goes totally on the beach drinking my ties no stress whatsoever Meanwhile back at the ranch or back at the enterprise would be the bet we see that Work continues because the agent keeps the context and silent enough breadcrumbs in her agent in her context loops in her her second brain To allow somebody to borrow with policy and with permissions What's necessary to keep that enterprise initiative going that to me is like the ultimate? business continuity Satisfaction if I was like CEO or investor somewhere like that's the world I want to live in as a knowledge worker as a business owner as an entrepreneur That's not one world. Yeah.

Yeah, and I think it's just you know the work working with agents, right? It just doesn't feel like work, right? It's just like you just like they're going off. Yeah, they're doing things for you You know and and it's it's really empowering for people I think you know we're used to building right we're used to coming up with ideas And then you just get in front of a keyboard and make that happen for most people They don't you know They don't they haven't experienced that of just thinking things up and making it happen So I think this is a huge unlock and it's just it's really really really profound for people who get started with the agents Well friends listening to this podcast go to nano CEO or nano co dot AI and I are the folks that made nano claw to build it for your enterprise or to fork it for your enterprise or Customize if you're an uprising for everyone else go to nano claw dot dev free as much as the possible could be an open source MIT licensed Thank you so much for being courageous enough to share that MIT and then still feel even after the fact nor regrets like I You've given me a new a new a new facet to consider run up and source.

I've been pretty sad. I would say like pretty Not I wouldn't say like sad necessarily like just bummed Maybe that's a version of sad but like some other adjective that describes sadness that isn't quite crying tears I'm not crying tears not yet at least but I was really feeling down about open source and like the reasons to do it and how you know There's just so much threat even from a security threat You got tried and true to open source out to that's not getting inundated with Security issues because their code is open right and you got all sorts of like inbound threats to anybody who makes an open source project Whether it's commercialize or non commercialize. I just feel pretty down about it But I like your lens I think I like your your altruistic tendencies when it comes to why you chose to do it initially And then while you haven't regretted it as part of and actually we've been into the fabric of your your business plan to use it as a As a benefit not a Achilles heel in any way she performance so cool. So friends go to those two places I'll give you so much for come on the pod man and sharing just a your agent thinking man your thoughts I really appreciate it.

I enjoyed this conversation so much appreciate you. Thank you Okay, this is the end you made it you've arrived This is the show where you can come for great deep conversations about the changing environments We're all in the embracing of this agent culture the agent world We're all living in the replatforming of our entire industry as we speak I'm both terrified and exhilarated at the exact same time I'm about you maybe that's true for you too You tell me and the easy way to do that is to go to changelog.com community it is free to join Zulip is where it's at maybe changing soon who knows Zulip has some changes I'm still evaluating it But for now Zulip is our home and you can chat with us and everyone else in the community right there Of course a big thank you to sponsor the show without them This show would not be possible got our friends over at build kite our friends at work O.S. and our friends at coder.com and of course to our partners at fly for giving our agents a home giving our agency computer Learn more at fly.io and it'll be freak in residence break master cylinder bring those beats. I'm not my head I hope you do too.

Thanks for tuning in and see you soon