Making OpenClaw Actually Remember Things

Aloha and welcome. Today we're going to fix long-term memory. So, I actually have OpenClaw installed on this Mac Mini right here. And so, this thing is actually running my whole entire life. And I noticed when I was chatting yesterday that my memory stuff wasn't really working after things compacted, it says like, "Hey, I didn't really know what was going on."

And so, what I found out was that there's this thing called QMD. And this is a new thing that came as part of the update that we're going to go ahead and talk about. We're also going to talk about here about OpenClaw. Basically, OpenClaw has now uh become in the hands of Open AI which is pretty amazing. So, Pete Steinberger is now joining the Open AI team and he's going to be basically helping them uh like I think they've set up a whole new foundation and everything like that and a lot of people are really concerned that this may actually tank the project or something like that and it's actually not. I'm also the belief of Alex Finn where he's also saying that it's very bullish and we're going to talk a little bit more about that.

So, we're also going to talk a little bit about the meter memory optimizer skill. So, I made a skill around this whole thing, and it's a little script that's going to check to make sure that your memory is pretty much compact. Cuz what most people don't realize is that certain files inside of your memory um can get really bloated so that every time you start to actually prompt your u openclaw agent, it'll start to like maybe use 2,000 tokens right now. A week from now, it could be 6,000 tokens. It could be 20,000 tokens. Cuz sometimes you'll say, "Hey, can you remember this? Can you remember that? Can you do this?" And it'll um by default want to put it into like an agents MD file or in these other places that don't always need to be there. So there's a way to actually store these memories in a progressive manner so that you don't always have to fill your context window. So this will actually make your agent a lot smarter, a lot more personal to you, and actually kind of remember things in conversations, especially for these long running tasks. So we're going to get into that a little bit today.

Uh this is an amazing live stream. So you're going to make sure you tune in. Uh because we have a whole bunch of people tuning in because we have Alex Finn in the building as well. So if you haven't got a chance to tune in, Alex Finn, he's also a mod. So if you talk any smack, my boy got you right there. Uh he also went crazy. He's got a couple Max Studios that he's going to be coming in. Uh huge shout out to Eagles worth as well. Uh and I appreciate the Pixel Collector for popping in. Uh also do make sure you do a favor right now. Just, you know, smash a thumbs up and share this with some other folks because right now, um it's not being posted to X right now for whatever reason. So, I'm going to see if I could repost that right now. Uh, so that we can get that going. So, let's go ahead and kind of do that as well. So, we got to take care of some of the the basic bills here. Uh, cuz right now, I think there's a problem with X posting somehow. And so, I'm just going to make sure that this gets reposted cuz as of now, the stream goes live. And you can kind of see it's not really on here yet for whatever reason. I have no clue. So, I have to go into here and then I have to like share the screen. So, I have to post this uh live now to fix open claw. memory for my agent. Okay, let's post this. Okay, so now that I've posted that, it should now start showing up on my stream because there's like zero people actually joining in.

Okay, cool. So, yeah, now that's other people should be posting up there. And so, okay, so now that we got that, we got Alex Finn here. Uh, and so he's talking about this use super memory AI. So, um, you know what's really interesting is that like I tried to look into this and I couldn't really find out a lot about the super memory AI um because I love Draabia actually. He's [clears throat] a really cool founder and stuff. Uh, and what I also found interesting is that um this there's stuff that's already built in that can work really really well. The thing about this type of app, which I may explore later on, depending on what happens, is the fact that like, you know, after about 3 million tokens, you're going to pay 20 bucks a month and then you only get like a,000 searches. And so this stuff can like really kind of lead up to a lot of stuff over time. The cool thing about like Open Claw is that there's it's open. So a lot of people are building stuff in real time. So you can actually like make something and open source it and put it in for free. So they already provide like a very basic let's just kind of like talk a little bit deeper right now on the memory system. A a lot of people don't really know about this stuff and I think you should probably learn about this because no one's really talking about this technically right um other than Alex Van and even Ross Mike and some other uh content creators.

So the memory system it's all documented here on the openclaw docs. Uh it's basically stuff is in plain markdown. So I'm going to show you really quick. I actually have because I have it running on my Mac Mini I can actually do a remote session inside and I can show you the workspace. So for my actual workspace, you'll see files like this. So this will explain kind of what happens. This is like first boot. This is exactly like kind of what happened, how we set up the Mac Mini. Uh and this goes through the various days. And then there's like an archives folder that I created to port over my chat GPT messages over uh onto this Mac. And so you'll also see like any indices that it creates as well uh that also got put over. So that's basically kind of you know the long and story short. It's like in your memory. The stuff will actually be in here. Uh, and the stuff will be archived. Uh, there's also a skills here. There's also some like overlay. This is like actual workspace that my um agent was using. So, this is stuff about the user. This is stuff about my soul. Uh, and then these are like anything else that we have in here. So, here's a memory thing. So, what ends up happening with a memory stuff is basically over time this will start to get filled up and every time you have a conversation, this gets loaded right in. Uh, there's also like an agents MD. So the agents MD file is the actual like instructions for how um if you've ever used claude code, if you've ever used any one of these coding agents, the agents MD basically steers the language model and that gets loaded every time in every conversation. And so a lot of times that file can get filled up pretty fast and start to kind of pollute things. And so if we kind of go back into here, basically you can see every single day you'll have a daily log that spits out. Uh it's going to read today and yesterday's session every time it starts up. And so what ends up happening as as the days go further, you don't have access to further days unless you actually specifically ask for something like that, right? And then this is a memory MD file. This is optional. This is curated stuff that gets filled up. So only load in the main private session, never in group context. And so uh these basically show you where they live. And this is the reason kind of why we're going over this is just to really understand how this type of system works here. And so um this is like there's an automatic memory flush as well. So when a session is close to auto completion uh it triggers a silent agentic turn. So this reminds the model to basically write any memory before the context is compacted. And so usually it'll do a flush and you can see the reservoir for the tokens floor is 20,000 tokens. Uh and then the threshold for the tokens 4,000. So this is a prompt that it writes basically to flush the memory. You can see it right here. Write any lasting notes into here before it does anything. And so there's a there's some other parameters you can also tweak here as well. So workspace must be writable obviously. And then there's a vector memory search. So this is the part that we're going to really talk about. This is kind of what somebody was mentioning about super memory versus the other things. So by default there's a vector memory search that can actually go in uh and this is cool but QMD is actual project. Let me see if I can find the QMD project. QMD uh GitHub. So QMD is is this project here. If you're actually wondering you can actually install this yourself. It's called a mini CLI search engine for your documentation. So these are knowledge bases, meeting notes, whatever. You can track your current state. And this is really, really good at searching markdown. And so the way that it works is that user gets a query. And all of this is free, by the way. This is free and open source. And this is why it's really, really cool. So you're not going to be trapped into paying, you know, 20 bucks a month or even 400 bucks a month for enterprise grade, you know, like this type of style stuff. Um, which is like it's cool, but if like all I'm doing is just it's just this guy on a Mac Mini, bro, like [laughter] you know what I mean? And I think this is kind of why I'm I really want to answer this and kind of fill in some of this technical backgrounds cuz there's a lot that's going on here and maybe people will hear the term QMD but they don't really realize like the importance uh and actually what's happening behind the scene when you're calling this type of stuff to get memory cuz this is a really complicated topic and it's still being discovered right now in the agentic world. So uh obviously you want things to be really fast, things to be kind of ranked up so that you can always get the information you need and relevant at the time and this is really important for your your agents as well.

So, uh, you can see there's different phases, right? When you ask something, you're basically your agent and or the actual framework is going to do a little bit of an expansion to try to understand what you're looking for. So, they have these fancy terms here that kind of spread out and then these types of things spread out to um like to search stuff through these different files. So, you'll see these key terms like BM25, vector search. I mean, you just have to kind of know that some fancy stuff is going on in the back end. Uh, and then for then what ends up happening is things will actually get ranked accordingly depending on what you're asking for. So like I can say, "Hey, what was that vacation plan that I had to Italy? Can you just bring it back up?" So it's going to be able to do this technique and bring up those information and say what was, you know, what was my packing list at the time? And you boom, you'll be able to pull that up pretty quick. And so this is pretty cool. This is free. So uh, previously you would have to go through these commands to point your agent to this specific directory and install it and it would download a little model. But now that's actually kind of baked into the actual um backend on the latest version. So if you have 2026 February 13th, so 2.13, you'll actually have this experimental backend thing. And if you don't, if you ask your agent to set up QMD, it's going to be like, "Hey, I don't know what that is." And you know, it might kind of go rogue.

So uh if you want to go ahead and do that, what I did for my agent is basically I just told it to go ahead and do an update. So this is my actual like chat conversation. And this is what you want to do is just say, "Hey, update yourself. OpenClaw 20262.15 is here." I just copied and pasted literally the tweet from the OpenClaw itself. So, OpenClaw, I just said, "Hey, update yourself. This is the latest version that's out." Uh, and it's really funny how it actually remembered that uh and it was actually was like, "Cool." And then basically it does it kicks off the update and um I even had an older update uh before. So, if you're on an older update before the rename, don't worry. Uh once the update is complete, you can do some other doctor commands, tell it to fix itself so that it uses the new open claw names. It can it's amazing how smart this thing is and at fixing itself. Uh but that's kind of the first step to get this thing updated. So like get make sure you're up to date to the latest thing. Uh and then make sure you get this thing going here.

So uh Telegram has a new feature called streaming which is really cool. So you'll start to see some of this text streaming in. So I said, "Yo, do we have anything to enable streaming?" So you make sure you go ahead and do that as well. Uh and I said, "Hey, this isn't streaming." And I basically had to quit the app and reopen it to get the streaming working. And so that was really cool. Uh and then you can do /reasoning obviously stream to see like the reasoning stream. So uh if you do slreasoning stream, you can actually turn the reasoning on or turn it off or like reasoning um like basically what ends up happening is one of them will actually you'll see a chat bubble filling in with the reasoning tokens and after the reasoning is done it will flip it out and show the response. So that way you're not like flooded with a bunch of reasoning, you know, messages and trying to scroll through, which can make it really annoying. But if you actually want to keep everything, you could just say just show me everything on, you know, and so you'll get separate messages for the streaming, which could be super handy. But right now, I just leave mines for reasoning stream. So that way I'll see the stream of thought. Uh, and then that way I can catch things if something breaks. So it's pretty cool. So like I said, you have the full combo. And now that it, you know, I make sure that the stuff was enabled, it's actually pulling up my Italy trip, right? So that was kind of cool there. Um, so and I said, "How do you use this tool or whatever you're using?" And that's kind of where I was pulling up QMD. Uh, and then so this is the problem that I was having is that sometimes people were saying that they're having some memory issues. And this is where we're going to actually go in and take a look at the memory fixing stuff. So I obviously had it says like, you know, take a look at my memory files and figure out what we're doing. And so in this conversation, I'm kind of showing you here is that um, what's the strategy that we should do? Just cutting it seems extreme because I didn't want to just remove memories from the file. And how do we do this? And so I have Exa Code and I have an Exa skill. So for those who are wondering, uh, my skills files are here and I have an Exa skill. I'm going to open source this. I'm going to release an open source repo. And right now, I think I have this currently in my Discord. So if you want to click my Discord, I actually have like an open claw like chat group and stuff like that in there. Uh, but basically I wrote these scripts myself. Uh, and I had the basically had the agents do it. But this uses the latest version of Exa Search. So Exa.AI is amazing at search. And there's this new thing called like instant search. So if you're not familiar, you basically pass a flag in called instant and like the search is faster than Brave. It scores higher than Brave and it's like you can find anything on the internet. I use it a lot for coding and it's incredibly phenomenal for finding GitHub repos, uh issues in GitHub, Discord, like conversations of people having issues and then proposed workaround fixes. It's amazing. Yeah, I I can't tell you how amazing that is. I wish I was paid for them. So Exa, [laughter] uh if you want to partner with me, definitely hit me up. Uh I I'm a huge advocate of of their stuff. But yeah, this this skill is something I'll open source. I also made a memory optimizer skill which basically we're going to talk about uh coming up here.

So uh this is how I basically was able to derive my memory optimizer skills because we did some research on how um like and and normally when I'm AI coding is basically I usually have multiple steps in which uh the I I my agentic software runs. So in a conversation I usually organize things by concern. And so I'll say, you know, I want to accomplish this task, right? It's like, you know, make me a ping-pong game or something. So I, you know, step by step, make no mistakes or something. You know, people really joke around about this, but uh you have to as an engineer think through this in different pieces. And so um what's nice about these agents is they can already start to do that themselves and self-organize. Uh, but you still have to be cautious about um every single conversation that you have because if it saves something and it keeps referencing that up, it's like, you know, it's like you have a table that you can never clear out because it's always kind of busy, right? So, you can't really think about things. And the same thing kind of happens here. This is usually done automatically, but as of right now, this this may be fixed in the future and I may do a poll request for this, but I'm still experimenting. This is kind of why I wanted to kind of I'm not really publicly posting this stuff yet because uh as a person who's watching this live stream, all you have to do is hit the thumbs up uh and then share this across with other people because this really helps the channel go a long way. If you're learning anything here, I've specifically turned off the ads because I kind of want to hang out with y'all and I don't want like an ad to get in the way when you first click in the stream because I, you know, I just hate that stuff. So, if you're watching on other platforms that are serving ads, just come over to this one here on YouTube. Uh and I've turned that off for now because I feel like this is kind of the best place to hang out.

All right. So, um, in this conversation, you can kind of see the research that it did. Uh, and then my agent's file started to kind of bloat over like 2,000 tokens. So, basically, I had some information about kind of what was going on in here. And you can kind of see what happened, right? So, it's like my agent's file was over 2,000 tokens. My memory was 2,000. Like, it just everything was kind of up. So, uh, that's 3,000 tokens if we basically do some types of optimization to save per turn. And so um what I ended up doing is just giving it some instructions to do some optimizations and like how we can actually slim things down. So uh the current target of the agents MD was over 2,000 um I think tokens, right? And after the optimizations we brought it down to 600. Same with memory and so forth because a lot of this stuff can just be recalled using QMD. And so um no information lost, same searchability, you just stop paying to load it every turn and the QMB already has it indexed.

So, want me to draft a slim version? So, uh, one of my favorite things to do with my, uh, Clawbot is to have it draft plans for me. Um, mostly because I just want to see what it's going to do. I'm an engineer, so I want to review them. But if you're not an engineer, it could also be helpful to learn to see what your agent's doing. I like to be a little bit more verbose in that sense. So, um, yeah, that's that's kind of what's up. Okay, so that's uh I love to see the madman shifting. Hey, thanks, man. Uh, I haven't got to the comments. I'm a little behind. Smash the like like button. Uh, if you're building team of agents, think about using the doctor role with a Phoenix protocol. What is this? I haven't I need to look into that. Uh, the freaking cron doesn't work. Oh, that's interesting. I have to check that out. Uh, and it's better than Q. What's better than QDM? Yeah, I'm kind of curious. What a coincidence. I'm working on the QMD skill right now. Yeah. So, what's nice is the QMD stuff is actually built into the project and the agent knows about it, which is super handy. Um, Alex and Ray stream the same day. Yeah, man. I saw him stream. I I was inspired, bro. This is so good. It was so good. Hey man, I really appreciate the love, dude. Yeah, AJ AJ is the one who put us on. By the way, if y'all don't know, AJ when we were walking in San Francisco was the one that actually put us on the whole thing. He's like, "Bro, have you heard of this thing called Claude?" I was like, "Nah, we got to pull up." So that's what's up. Yeah. Aloha. Uh, pulling up for the support. Yeah. Creating assistant uses agent almost OpenClaw. Oh, interesting. Yeah. Also, big shouts out to to Vladimir as well. I appreciate that. Yeah, super memory AI. Okay, we'll talk about that. Cool.

All right. So, um, yeah, I'm I'm curious about managing tokens. And this just goes from my AI coding days, right? So, um in here, um what I ended up doing, I was like, great, we should have something that is done at night almost like the way human dreams. I want I try to connect the dots on what happened and we clean up these things so we force helping Ray achieve his goals. Uh, and then in the morning, we can give a report about what has been done. So basically, I'm telling my agent that I want to have a dream at night, kind of clean up these memories because sometimes the memories can get filled up and they're not always pertinent to what our goals are. So we're giving the instructions to the agent to make these types of things so it can learn for itself and help us out. So this is kind of forcing the agent down this route to cuz otherwise it's just going to keep doing what it's doing unless it has some directions from you. Uh, so this is the moment I thought this is a really good point for us to share back and forth and I wanted to give you this insight. So this is basically what it did. It gave us a dream cycle. So it's going to generate two cron jobs. One that dreams at night and then one that has a morning brief. And so in the latest update, there's actually some commands that it runs so that it can either run silently or run verbose and tell you what happened. And so this is basically what we did. Uh, so here's the full picture. And so we're going to basically go from 7,869 characters from the agents MD file. So, that was the file that's loading up some of my context down to 1,354, which is about 383 tokens, which basically removed a lot of duplication and different types of things. We thinned out the memory MD file from 7,000 characters to 1,000, which is super 1,600. Super amazing, right? And then it created some and some new folders in there. And so stuff that are in these folders are actually going to get Q indexed by that QMD thing. So, uh, this is looking pretty good. And I said, "Now let's go ahead and execute it." So that was kind of the more import the very important part there.

So uh once it did that um we're pretty much good there. So in order for you to set up QMD, all you have to do is just tell the agent to set up QMD. Literally just saying "Hey, make sure you're up to date and just say enable QMD. I want to go ahead and enable the memory back end to be QMD." That's it. And if you want, you could even just go to where it says memory openclaw docs and just paste in this type of thing. It will already know what to do with it. So this is basically what it's going to do. It's going to go ahead and install that into your actual thing, configure it, and it's going to um like do this type of thing. So, it says how the sidecar runs. The gateway basically writes a self-contained QMD home under agents agent ID QMD, and it collects the created uh collections in there and now initializes QMD manager on startup. So, periodic uh update timers, usually every 5 minutes uh will get armed before the first memory search call.

So, this is going to be awesome because um not only do I have memories in my actual uh repo here, but I also have um like if I have memory, I go to archives. I have imports. So, I imported all of my chat GPT history going back from like 2023 all the way back to like today. So, all of these are like my chat GPT histories, but the chat GPT history is only like the summaries. So, these are all like little summaries here. Same with Claude. So Claude from 2023 is all the way up in here. So now I have a space in which my agent I can ask any questions about anything like I asked about that Italy trip that was in 2023 that was in a chat GPT chat right and also when claude so it pulled them both together and pulled all the relevant information. It was amazing right? So this is how powerful this stuff is and then also have cloud projects. So all of my cloud projects are in here as well. And for you to export them, you just have to go to your settings in chat GPT or go into um OpenAI and just say, "Hey, uh go to the data controls and say export. I want to export all my data." So, as a California resident and maybe some places in Europe, uh given the data privacy laws, you're actually allowed to export whatever data this company has about you, which means usually all your previous chats and so forth. They usually just give you this zip file of stuff and they just said, "YOLO, here you go." it's not really well organized, but in today's world of AI agents, you can tell them that um you know, I have a my first live stream, I think I talked about how I walk through that specific process. So, if you want to know more, just drop a comment and I'll I'll kind of show you some more stuff there. Uh also, please excuse the noise. I just have a current like a wireless microphone on and uh we're kind of going through this thing and I think there's some construction that's happening across the street. So, um yeah, I don't think it's that bad. I have a little processor on for vocals and stuff, but that's what's up.

All right. So, that's what QMD is going to do. Searches through here. Uh, and you can kind of see what it's doing here, right? It kind of sets itself up. So, you can kind of get read about some of the technicals there. All right. So, that's that thing there. So, once you have QMD set up, you want to uh run the doctor command and it's going to tell you that if it's, you know, set up or if it come uh ran through any errors. And so, uh, after that, you're pretty much good to go. And so, one of the things that I want to share with y'all is this memory optimizer skill. So this is going to run when my device at night is doing its streaming and it's going to run this script and this script basically just checks the various like agents MD soul files and so forth and this is the like the tier one files right now. So the in this tier one path, basically what ends up happening, it tries to check to see how big your file is. And so if your actual file is kind of getting out of scope or it's getting a little growing a little too crazy, it actually starts to call it out, right? So it starts to do a scrub of that. And this is kind of what you know, these are the files that we call out. So these are the injected file, these are the files that we have here. Uh, and then these are the actual um uh directories that it's going to work through for everything. So uh and then it's going to actually give it a recommendation. So, at night while it's dreaming, it's also going to do this cleanup task to make sure that we aren't bloating up our memories. And this is really, really cool.

So, this is part of a skill file. Uh, and this is the actual instructions for what I call the dream cycle or morning brief. And in here, uh, the dream cycle is going to review today's files, search session transcripts, and connect the dots for recent days and reoccurring patterns. So, you can you can also just take this and just explain it to your agent that you want it to do something like this. And you can build your own version of this, by the way. You don't have to take mine. Uh, but this is something that um you know I'm I'm sharing with you to kind of give you some inspiration so you can kind of understand how to talk to these things and and make the right software for you to do these things. So these are skills, right? Um, you can literally get screenshots of here and just start throwing them into your agent. Say, "Hey, Ray did this cool thing. Can you learn about this? I want to do this for myself too." So um that's what's cool. This is the morning brief. And your morning brief you can describe however you want it, but this is just a good starting point for me. This is what I'm started to do. Uh, and so there's a configuration thing that they called session target isolated and set delivery announce. So you can kind of see for my um dream cycle at night, I have delivery none. It's silent. Basically, no message to the user. So you can do that. Uh, you can run tasks that are cron tasks that aren't going to deliver messages to you because you don't want them I don't want to see what it's doing for the cleanup. Uh, you know, I'll get a report, something like that. And so we have two different jobs. Obviously, um, like the dream stuff should be silent. The morning brief is kind of lightweight, conversational. So, it just encourages me to start talking to my agent and kind of point in the direction of where I want to go, which I find very, very helpful. And so, um, here's an actual template that it's going to run for the dream cycle. Uh, and also the the morning brief template as well. And so, this is, um, this there. And then this is the actual skill file that gets installed. And so, in the skill file, it basically describes everything that we're talking about how the open claw injects workspace files here in the context window for every single model call. And so the default templates in the organic growth cause these files to bloat over time. And so they basically waste thousands of tokens per turn. And so here's the optimization u workflow that you can actually do. And then you can actually um this is just instructions for the agent for it to do its type of optimizations there. Uh, so this is where it is applying things and this is where the dream cycle kind of kicks off. Uh, and it says never delete information. Move it to searchable. So it's going to move information into the memory and then star MD files and then always create drafts first. So create drafts and draft and show the user before applying. Uh, respect the soulm personally it's worth tokens uh do not optimize it away. Uh, and the convention must be self-documenting. So put uh memory notes in agents MD so future sessions follow uh them and put the rationale in convention so it's searchable and not loaded on every turn.

Cool. And then here's some actual templates for the actual agents MD. So this is what's going to keep the agent uh in scope. So it's going to reference this and it's going to say okay cool. This is kind of how I should organize the information that I dream about at night in a way that I can keep loading up for every conversation so I understand what's going on in Ray's life. Obviously, you'll want to tune this to your own thing, but I haven't publicly published this cuz I'm still refining this and uh this is something that, you know, my Discord members have access to. I haven't dropped this specific thing cuz I literally just made this this morning and I'm going to put that into the Discord right after the stream so that way the folks there can have it there. uh and you can experiment and kind of take it yourself. So that's memory MD template. Uh here's the memory conversion uh conventions template MD. So this is kind of the way that I would describe um like how these conventions are made. So if there is something that's going on, it will like after the audit, it'll kind of do this stuff in here. So it'll tell me like, hey, this is kind of how we this is what we found and this is kind of what was bloated. Uh, and so this three tier system is based off of the research that I was doing to understand u progressive disclosure for memory. So um progressive disclosure and what I'm trying to say here is you know like when you have a an agent has a task they're going to consume some memory to put into the context window to do some type of action. And so in here as you can see there's three different levels. One is like every single time you ask it, it's going to load up the agent's ID, the memory, the soul, and that's kind of what gives life to the agent. But there's other things that you don't necessarily need. You don't need like the 50 grocery list items in the conversation for every single thing you're doing. Cuz you could be asking it about generating images for this, launching a sub agent to go, you know, do some research for you. And like if it always keeps loading the grocery list in those tasks, then it's not really that useful, right? So that's where you kind of want to extract some of those files out. Uh, and when because it's it's working on a task, the agents are smart enough to know. It's like, oh, I'm working on a grocery tasks and I know that we stash those files over here because my agents file shows me that, you know, there's an index saying grocery list that's still active. I'm going to go now. I'm going to go grab that. So, that's kind of why it's called progressive disclosure. Whenever the agent's doing a task, you don't always want to um, you know, flood that desk space with everything it needs. It's only at the time that it needs it. Like, I need a hammer now. Let me go down to the tool shed. uh because my little thing says that the hammer's in the tool shed, you know. Um, and so that's kind of the way that you want to think about these conventions, but you don't really have to think about them too much because I kind of done some of the research for you. Uh, and and but you can also talk to the agent and have this conversation back and forth so you can learn as well.

So, uh, that's kind of what it is. So, in tier one, it's what I call like very expensive. So, like I'm telling the agents that this is the the three- tier memory system and each has different costs and characteristics associated with it. Right? This is not me making this up. This is from my coding experience but also cloud code SDK you can look this up. All of this is publicly documented. Uh and also the codebase. So if you look at the codebase from uh openclaw which is on GitHub it's open source. This is the amazing reason why it's open source and this is the big reason why Peter wants to keep this open source and that's why open uh AI has created a whole foundation so that we can actually see the code and see what's going on. Right? I can't see into chat GPT memories but I can see into the code for open claw and see what it's doing. Right? So, this is really cool and it allows me to actually talk to you and us have a discussion on what's the best approach and then I can make my own changes and see if it works really well. Obviously, this is something that not everyone's going to be able to do. But, I'm going to keep sharing this stuff and if you like this type of thing, definitely subscribe because this is probably like the most life-changing thing right now uh on the internet for a good reason. And I think there's a lot of potential here in it as a product. So, I'm really excited about how this stuff really really works um at a low level, at a in code level. And I don't know everything, but I just know how to ask agents, how to ask me to figure out how we can find this information. So, obviously, this is how everything's set up. You don't even have to know how this like code works, but I'm just kind of walking you through, you know, what is tier one, what is like this is all read from the code, and this is exactly explaining um what's what's what stuff is put in there. So, only put information here that genuinely affects every single interaction orientation, not encyclopedia. So, that's pretty cool. Uh, and then what we call tier two, this is searchable, and this is on demand. This is what's like considered cheap. So anything in the memory files are indexed by open clauses memory indexer. So that's going to be the QMD thing that we talked about earlier. So they cost zero tokens until the agent explicitly searches for them and retrieves them. And so that's the memory stuff with the daily logs. That's anything that has memory/topic and anything that's in there like brand guides, project notes, things that we'll talk about and they'll get pulled up just naturally through QMD. So that's really cool. And then there's a full fire read. This can be on demand. So uh anything that's on disk, the agent can obviously read that and only like tool tokens and all that stuff will get loaded. So uh that's the progressive disclosure pattern. Uh, and the memory MB basically will just now act as a table of contents. So this is a a term that I also used a lot in um when I was AI coding as well. So like the agents MD behaves the same way and in cloud code SDK the things behaves the same way. And basically the way this works you can nest memory files. So you can nest either memory or you can nest agents MD files in different folders and they can tell it like it's almost literally like having a signpost in a freeway. So if you're exiting on a freeway, it's going to tell you what the names of the roads are before you get there, right? So you're like, "Okay, that's the exit I need to take because I need to get off on, you know, whatever McDonald's lane or something like that or those types of things." And that's kind of the way you think about them is like every single turn is going to be a new folder. And if you have like a agents MD or if you have like a memory file that's in there, it's going to really kind of point to the next direction of where the agent should go. So that way it doesn't get overwhelmed, right? And that's the way that you kind of want to treat this type of thing here. Uh, and this will tell it what to focus on or like what key preferences and bullet points. So, uh, this also describes the bloat patterns which are super important. So agents uh will bloat if they like I was telling you a little bit earlier about um these different files and how important it is to kind of keep them lightweight but also provide these little indexes so that it can start to crawl through. And the way you want to think about them is like literally like an encyclopedia index, right? Uh, you can't memorize everything but if you know where to find where the cheetah is then you can go to the C section and start to search up and see what's kind of in there. So uh that's basically that. Uh here's the target token budgets and that's pretty much that.

So this file is installed as a skill in my actual agent. And so in my agent uh we can actually see it here as a skill file. This is a memory optimizer and you can kind of see how it organizes itself in here. So this has like a dream cycle. These are the templates and this is the tiered system and here's the scripts. So that's the audit script that's there. Uh and this is the skill file that we talked about earlier that's sits in there and um when the agent kicks off to do um its like cron task to dream at night, it's going to know to to pull that information. So like here are some example skills and stuff like that. Uh, let's see if I can pull this up here. So this will just define like what specific skills I have, what coding agents I have, what specific, you know, tooling that I have in here. Uh, so that's kind of get what what gets loaded in and I don't have to keep describing it over and over again. Uh, so that's basically a big primer on memory and all of this stuff is documented in the code in the documentation. It's a little bit complicated to read, but if you haven't set it up, like kind of long story short again is make sure you talk to your agents and get the latest update. So, if you just go to like literally copy and paste and say, "Hey, open claw now as 2026.2.15. Go ahead and update yourself to this version," do the update. The next thing you want to do is like, "Okay, I want to take advantage of open clauses QMD. So, uh, I want, you know, this is an experimental thing, and I want to go ahead and make sure that we have this enabled for my memory." And so once it goes and gets that set up, you let it do its thing. Uh, and it's going to do its installs and stuff and it'll be good to go. Uh, and then um then the the last step is um you can take some of this research that I did. I'm about to open source it. Uh, but first I just have this currently in my Discord. Uh, and you know I I did some research and I kind of walked you through a little bit earlier of how I had this conversation with my agent so that we can basically create the system so that it would do dreams at night. So, my concept is for it to dream uh and then give me a morning brief cycle. So, with that dream cycle, basically what we're doing is just kind of cleaning things up at night, making sure there isn't too much contact stuff into too many areas so that way I keep things really efficient for my agent to do work that it needs to do um for what we're doing. So, I think that's kind of like the highle summary of it all. And I feel like there's a lot to talk about just even within these things, but um I wanted to pack everything in as much as possible into like this live stream. And I'm going to get into some questions next so that way I'll answer you guys' questions because there's probably a lot of y'all in the chat right now who want to have who have a lot of questions and want to get things answered. So

I'm going to definitely try to see if I can tackle those, um, before I basically head to the beach, right? So [laughter] let's go ahead and start to take a look at that.

So, open source it, man. Uh, 15 bucks a month is tough. Yeah, I got you. Um, I have people who do pay that 15 bucks a month right now, and those are my members, and I want to make sure that they're taken care of. But they're also, um, my early adopters, and so they give me that feedback and refine it so that by the time it gets to you, uh, it's more refined and like you don't have like as many crazy issues. And I'm not saying that there's crazy issues, but I feel like that's a perk of having that type of thing. And I know not everyone can do it, and so I want to make sure that, you know, that I mean, that's why I have these perks. Uh, and I also can't deal with everyone's issues, uh, as another part of it. There's only one of me. And people who are able to pay into the Discord, you know, have some like general, like huge amount of interest in something like this. And so, uh, or they have the discretionary income. And so it's just another type of thing that kind of helps me eliminate because I have hundreds of DMs from, I don't know if they're bots. I don't know what's going on. I mean, a lot of people can send DMs and stuff. So that's another tough problem to have. But I definitely appreciate.

So, if you can't pay the money, you can also, you know, watch this. Literally, just watch these type of live streams, the stuff that I do for free. And so, my goal is to literally live stream on the weekends. So, usually Thursdays, usually on Saturdays and Sundays. Uh, but today during the week, I'm going to do some extra streams cuz I've been kind of, uh, shifting my situation right now. Um, with, you know, being in Hawaii, obviously. Uh, and so your support goes a long way. All you have to do is literally just watch the stream. I turned off ads for you, so you can actually watch right now. Um, so there's a lot of different ways to support the channel. Literally just liking, sharing it with another friend, subscribing goes a really long ways, too. And this will be available for those like, uh, you know, who can't do that 15 bucks a month, you know, later on. Uh, so definitely stay tuned for that as well.

Uh, have you saw Kimmy Claw? I saw that Kimmy offers Claw, and also BU now also offers Open Claw as well. So BU, as a company, offers it, which is like the Google of, you know, China, which is really fascinating. Uh, hey Paul, how's it going? Welcome, man. Uh, I love your new live stream setup, by the way, with eCam Live. It's so cool. If you haven't had a chance, Paul goes like crazy. He's been, he's been all in on Codeex, and he's been doing some really cool demos. If you're into iOS development, he has a lot of great material on how he uses it for iOS development. He's been playing a lot with Spark recently. So, Spark is the latest coding, um, like super fast inference that is provided by OpenAI, and he's made some games and he's doing some really cool stuff in that space. So, definitely go ahead and check out Paul if you haven't had a chance. Uh, he's really, really cool. Uh, Domingo, thank you so much for joining in. Uh, Stefan, idea, fire idea. I think this is for the memories and stuff. Uh, this is pretty dope. Yeah, I mean, any questions you guys have, let me know.

How do you have Open Claw search the internet through Brave without getting prompt injected or search the internet in general without running into an issue? So, there are a couple different things. I try to steer it to specific sites that I know like are pretty safe. So, I mostly just point it up to the official documentation from Open Claw, right? And a lot of times I'm more so reviewing it myself on my phone anyways. So, I'm just giving it random snippets of things. I don't necessarily actually, I don't even have Brave enabled on my agents. I only have XAI. So, Exa AI is my primary search engine. And so, like they have a search feature there. And I also have a skill that I'm going to share that's open source, but you can literally just point it your agent to the XAI, give it the API key. And, um, a lot of those data sets are already pre, um, like filtered out. So, you're not picking up a lot of junk. You're only picking up the specific inquiry information or queries that your agents need. So, Exa AI has a specific thing called Exa Code, especially for code-related tasks. It's extremely good at searching through GitHub, searching through documentation. It's not going to prevent, uh, prompt injection, but it reduces a lot of the likelihood behind them. And so, I'm pretty sure this is another billion-dollar industry is to have data sets from Exa like that, uh, that are pretty much, you know, like filtered out even more.

Another MCP tool I like is called ref.tools, and I use a lot for AI coding. So, I'm trying to figure out how I can get a script or CLI for that. So I could just use my API key and have it, you know, because I'm doing most of this stuff is doing coding tasks for my agents. Uh, you know, so they're basically doing that type of thing. But yeah, it's a good question. U obviously, you have to be aware that this is a possible thing.

So, what's the Anthropic Pentagon thing that's going on? I haven't followed too closely on that. Um, let me see. Anthropic Pentagon. Let's see what's going on here. Exclusive Pentagon warns Anthropic will pay a price for as feud escalates. Okay. Wait, wait, wait. This just happened right now. This is like breaking news. Breaking news. Breaking news. Okay. So, what is what is going on, bro? Axios exclusive Pentagon use Anthropic's Claw in Maduro, Venezuela, right? Wow. Anthropic won't give Pentagon unrestricted access to its models. The Pentagon threatens to cut Anthropic's in AI safeguards dispute. Oh my god, bro. This is crazy right now. So, what is this? So, I don't know. I'm reviewing it. I can't even scroll on half these sites. Okay, I'm blocked everywhere. Um, saying that while having the decoder, can we actually open? I can't even read any of these links. Uh, come on, bro. Like, these are, you see why we need AI. Like, this is kind of trash.

All right, so Anthropic continues to refuse the Pentagon unrestricted access to its AI models. Oh, so the AI, the Pentagon is literally asking for unrestricted access, and they're like, "Bro, we just can't give you the keys because this can get into bad actors' hands, and we know when that happens." Have they ever talked to Ply the Prompter? Like, do they know who that is? Like, they should just go talk to Ply. That guy can like jailbreak these models in five, not even five minutes, bro. Like, he just one prompt. >> But I, I think I know what's going on here. If I think, kind of read between the lines, this is kind of what I'm thinking is that the government wants to have this because they can already do it. And if Ply can do it in one prompt, they're not saying that they need to do this. They're posturing that the company should allow this as a back door, right? Like that's the same problem. It's like if you give like a thug your key or something to your house, he's going to give it to someone else that pays him a lot of money, and then all of a sudden everyone else has access to your house, right? Like that's not a good thing to do. And I feel like, yeah, I mean [laughter and gasps] I think that's dangerous if you know what I mean. So, yeah, I don't know. I mean, yeah.

So, insist on drawing the line at two things: mass surveillance of US citizens and fully autonomous weapons. So, a senior government official told Axios that negotiating individual use cases with Anthropic isn't practical. So, OpenAI, Google, and XAI have been willing to work with the Pentagon. The official said, uh, all three have agreed. Okay.

So, a lot of times, this is kind of where, um, I have a skill that I'm going to open source. Uh, I'm going to Claw.ai. I need to drop it into my agent and install this. But basically, what I do is try to check for like fluff and stuff. Uh, can you review this document? Okay. News, this, uh, news article, and use my truth skill to help me figure out what is real. So, I made a skill. I have an app called Truth Torch, and I'm basically turning it into a CLI/skill so that way my agents will do this. Uh, and so, yeah, rhetorical analyzer skills. So, I'll show you the output. This is really, really cool. So, a lot of times when you read news, a lot of times they'll like write it in this way where they'll try to pin one thing against the other, and then they'll add other claims but not back them up. And they'll either back them up by emotion, they'll like forgive facts and all this other crazy stuff. And so, this is kind of what's cool. So, now it's, uh, Anthropic, uh, I'm using Anthropic's like models to do these types of skill checking for me. So, you can see it's doing all this stuff on the internet to check all these claims of what's going on. And so, now it outputs it as a skill. So, this is really cool because I can now hand this off to my own agents. And so, I made this skill in Claude code, and this skill is totally transferable to everyone else. U, so Anthropic is refusing to give the Pentagon unrestricted use of Claude, insisting on guardrails against mass surveillance, and the Pentagon is threatening to end a $200 million contract as a result. So, here's the core point. Anthropic draws two red lines: no mass surveillance of Americans, no autonomous weapons, and the Pentagon wants an all lawful purposes standard with no company-imposed restrictions. So, Open, Google are more than willing to comply with Pentagon demands. Dario Amadoré published an essay articulating why democracies shouldn't use AI in ways to make them resemble autocracies. Uh, and so this is a system of government by which one person has absolute power. Facts. Uh, the dispute is happening against the backdrop of ICE shootings in Minneapolis and Anthropic's Palantir Partnership. Oh, interesting. Okay. Okay. What they say, what they actually want to say. See, this is this is this is why I love using this stuff. Um, yeah, I'm definitely going to share this. I'm, I'm dropping this on the Discord. I'm going to drop this right now on the Discord. [laughter] This is too good. This is this skill is too good. We need this. And I, I will open source this. Um, let me address. I have so many good skills right now. Uh, let's see. Capabilities. Yeah. Yeah. Yeah. Yeah. It's, this is what we have to use AI for. I have a crypto scheme evaluator, too, which is pretty fire. Um, it's based off the same rhetorical analyzer. Uh, download. Cool. I'm going to put this in the Discord. Discord. Okay. Oh. Oh, shoot. I'm going to mess up my thing. Okay. So, here is my general, and I'm going to put this in skill. I have a skills chat. This is skills. I'm going to create one. Rhetorical analyzer. There we go. Rtorical. Here we go. Enter. And then I'm going to post this. And then I'm going to post it in here. Hold on. My bad. I'm going to drag the file up in here. So, this is rhetorical analyzer skill. Okay, cool. Uh, here you go. Perfect. Okay, so you can download it here, and I have this skill file. So, that way you can install it, and so it's a skill file, and you just give this to your agent, and it'll know what to do. Uh, but yeah, so folks in the Discord, you definitely have that. So, that'll be in the, um, community section. I have a little Claw. I have a skills actual like post type of thing. And I also have an app architect skill. This one is incredibly fire. If you haven't had a chance, this, this is what I use to build apps, uh, and basically one-shot them. More on that soon. So, yeah, this is basically how I organize the skill. It's a pretty simple thing. Do I have the code files also? I think I have some other stuff. Okay.

Anyways, um, as you can see how this is amazing, how and how good it is. So, Anthropic is a principled. Okay. So, Anthropic's principled holdout among AI companies, but that's principled stance is complicated by its existing defense contracts and financial interests. See, I don't know a lot about the background. So, now I can actually start to kind of ask more questions, right? That's the whole point. Rhetorical analysis, right? Like, you want to have a co-pilot to help you think about these things, right? The evidence proof table. So, the Pentagon is considering ending an Anthropic partnership. Axios reported the sighting, and this is confirmed by these other sources. And now we also have a claim about a $200 million contract stake, and this is a, obviously confirmed, confirmed. Uh, Pentagon renamed Department of War, referenced casually, confirmed Trump administration rebranding, January 9th AI strategy memo, article claims no link provider but referenced by Reuters in the original reporting. Uh, OpenAI, XI, Google. So, this is anonymous senior government officials. So, single anonymous sources, companies haven't confirmed publicly. So, this is actually like a thing to kind of call out, which I find super helpful. Uh, one of the three alleged all lawful purposes. So, this is the same anonymous official, right? Unverifiable. Uh, Dario Amadoré blog post, real essay, fatal shootings, obviously, and so forth. So, the article doesn't mention that Claude was actually used in the Maduro raid via Palantir, which is a massive piece of context that came out of that WSJ reporting and significantly complicates Amadoré, uh, Anthropic's principled stance narrative. So, uh, here's the rhetorical appeals. So, they use ethos and pathos, like, so they try to use the credibility on on these types of things and his own words, and this is like the sourcing for the claims. Uh, and they use emotion here. So, they try to like, this is where it gets interesting. So, the article juxtaposes Anthropic's ethical stance against the recent things that happened in Minneapolis, uh, and the Palantir ICE thing. So, that's really interesting. And here's the actual like logos chain, right? So, this is how the thinking actually works, and that's is why Opus is an incredible research model, right? Um, you can point it at a skill like this, and it actually starts to think like a lawyer. It's just, all I gave it was a text file, and like, look at this, like we're analyzing an article like a, a way a PhD law student or something would be thinking through these things. And it's helpful for me because now it cuts, it cuts through the fluff, right? Uh, and I'm not getting all worked up emotionally just from reading an article. I'm just kind of trying to think about them from first principles. Uh, so here's like unexamined assumptions for this whole article, and then the steelman version, and like what's actually missing. So, this is kind of crazy, right? So, um, yeah, this is bottom line for you. The facts in this article, check out the framing is slightly sympathetic to Anthropic, but not dishonestly. So, the biggest thing is it underplays the Maduro raid and the Palantir pipeline, which complicate the principled holdout narrative significantly. This is a real developing high-stakes story with today's supply chain risk, uh, threat being a major escalation worth watching. Cool. Now I can give this skill to my agent, and then my agent will be able to do this. So, I can just give it an article, say, "Hey, can you take a look at this article and just kind of run this through me?" Uh, and then you can tell it to reshape whatever responses you have. This is the way I like to read information, but you can take a skill file and have it reimagine for you. But look at at what it did for the research, right? It did all this research for me, like 10, 20, 30 different results from all these different types of things from all these different organizations. Um, NBC News, Wikipedia, NPR. That's faster than I could do it. You know, I didn't spend the whole thing. So, that's really, really cool. Um, okay, cool. That's what's up. Uh, let's see what's going on here. So, yeah. Uh, let's see what's going on. Also, Ray Fernando, you might have missed it, but Alex, uh, was in the chat. Yes, I think I missed it a little bit earlier. My bad. Uh, even check writer's article. Yeah. During the viddles. Yeah. Uh, it likes GT5 Nano using open router with auto results. Mahalo. Hey, thank you so much. Uh, my Open Claw is named Clauddio Alaka Alaka. Uh, you were instrumental in my original setup of Open Claw. Excited to see what you got cooking. Yeah, mine is called Honu. [laughter and gasps] That's awesome, man. I really, uh, I love that name, Clauddio. That's so cool. Uh, drop the link to join your Discord on X. Oh, yeah. So, if you're on X right now, let me see. X.com. It's RF.me Ray Fernando. So, this is my live right now, and I'll put this in here. See, it's kind of weird watching me. RFR.meisord. I think you'll, yeah. Okay. So, I just dropped a link for the Discord. Uh, and if you haven't had a chance, you know, go ahead and check it out there. It's also pinned here. If you're on YouTube, you can check out the comment there. So, rvr.mmeisord. That way, you can see here, um, if you want to go ahead and join the Discord as well. So, yeah, that's what's up. Uh, I haven't seen the message. I'm still kind of scrolling back right now because I'm a little bit behind on the chat, but I wanted to make sure I cover some of the messages. Wayne, [gasps] oh, I have so many good skills right now. Yes, how's it going, Wayne? Thank you so much. Uh, Wayne over from Convex. I appreciate you guys supporting the, uh, the streams and supporting everything you guys do. I mean, you provided the space. Uh, we had a fire episode two for our, um, Thursday vibe check. So, that was really amazing. Alex Finn is in the building, kind of doing some demos. This is when things were really heating up. So, uh, that's what's up. Yo. Yeah, I got you, fam. That's a really nice skill to have. Yeah. Uh, rhetorical analysis skills is definitely fire. Uh, let's see. Okay, cool. Uh, Anthropic has been feeling themselves trying to control everyone's behavior. This is going back, uh, backfire. Yeah, I mean, I could see that too. Could be a rough time to invest in Anthropic. Yeah, Alex Finn official. [gasps] Uh, who wins the government contract to set for a long time? Yeah, I just got them at. Oh, yeah. So, he's got another Mac Studio about to set up a bunch of local models. So, this guy is absolutely destroying it. Alex is going crazy. He just sent me a picture of like two of them, and I think he already has one, and I think there's a couple more, right? This guy's gonna, >> Bro, they're going to break into your house, bro. You better watch out. Oh, okay. Yo, how you living? Okay, cool. Uh, Alex, crazy, right? Consider Anthropic a supply chain risk. Um, okay. Let's see. Thank you. Answer is very helpful. Um, please don't repeat everything you said in the last hour. Okay, so unconverted. Oh, okay. Cool. I converted, um, vision and text to Core ML, and I have [gasps] Whoa, this is crazy. Um, so you're trying to deploy, um, create custom VMs to deploy on AWS. Any advice? I don't know if I have much advice because you're just, what are you trying to do with the Core ML stuff? Like, you have like those separate, right? And then you create custom VMs to deploy on AWS. I mean, my only advice is to ask Opus 4.6 or Codeex, and to have you use ExaCode or ref.tools to like, literally just say, "This, this is what I got. This is what I want to accomplish. Help me walk me through that process." And it'll take you through those steps to to do that. Um, that's basically how I got my Cloudbot set up, you know, like with AJ. So, AJ walked me through how to get stuff set up in AWS. And then afterwards, like I set policies, I like locked it down, I was doing all kinds of cool stuff. And I learned a lot about the AWS infrastructure just by talking to, you know, in this case, Opus 4.5 at that time. Uh, and it was super helpful. And I even just fed it screenshots of stuff. But you can control a lot of things through command line. And I actually think that AWS is easier to control over command line than it is over the UI. It's kind of funny, actually. So, yeah, uh, that's probably my best bet if you're thinking about that. So, um, let's see what's going on. I'm a little bit behind. Do you ever receive token mismatch error? I haven't seen that yet. Um, I don't get Claw to produce HTML reports, but, um, I think I did once. I'm going to hook up my Claw up to Notion, and so I'm going to have a lot of like different reports and various things going into Notion. I have, I have a lot of workflows in Notion, so I'm going to basically do that as well.

Hey, from the UK, I'm concerned of redownloading the bad skill code. Where should I get QMD or is it already installed? So, QMD is already installed as part of the Open Claw repo. So, you could just literally point it to the official documentation. I'll always, I always say, stick to the official documentation and then give it links sometimes, uh, and it's going to know a lot about that. So, uh, and as far as skills, sometimes I take other people's skills and I read through them, and then I try to like prompt my agent to build them, not necessarily looking at their skill and say, like, "Oh, I like that." So, I try to basically make my own specs in, in some ways, and then iterate back and forth. So, just like I do with coding, sometimes I go into plan mode. So, I tell my agent, uh, or Honu, in this case, that, uh, I want to do a little bit of planning before I execute on making the skills, so that we can kind of have this back and forth conversation. I would say that's more advanced mode. I don't think everyone should be doing that, but as an engineer, I want to make sure all the details are implemented correctly, and, um, you know, I think that's kind of what's up. South by Southwest AJ. Oh, I need to be going there. Yes. Uh, so QMD for those who are wondering, it's a query markup document. So, this is just a fast way to be able to search through your documents, especially if it's written in markdown. So, this guy came up with this great technique to do that. I think he's from Shopify, and um, it's super important, especially in this age. What's nice is basically that you don't have to pay a bunch of money, as we saw, like once you start querying up to the millions of documents, you can pay upwards of, you know, $20 a month to like $300 to $400 a month for stuff like that. And so, you basically get that for free, and your agent gets to use that on-device, which is really, really cool. So, uh, going to hop on the Discord and see what, uh, I can derive. Mahal, thanks, man. Yeah. And let me know what skills and things you want to see. I'm going to probably start putting this stuff in the chat right now. So, I'm running it on my MacBook Air. Uh, working on how to get infr set up for a couple hundred sales reps. Wow. Uh, okay. That's what's cool. Uh, the locally hosted model. Okay. So, the way that you want to think about this, if you're serving stuff locally, you can use like Tailscale or something, and then, um, you'll set up something where you'll serve it. Like, right now, on the Spark, you can just tell, like an Nvidia Spark, you can, like, I could serve models from it. Um, if you're serving on like MLX, there's like a serve command. Uh, LM Studio also provides it for free. Uh, Ollama, depending on whatever you're using, you know, MLX stuff, uh, you can serve that back out. So, you're basically turning your Mac into a server, and if you have Tailscale, you're basically going to create a tunnel, and from that, you're going to basically have AWS or whatever your your agents are going to use, and it's going to be, you know, know about the specific tunnel, um, that it can, you know, has access to communicate to and start to send requests towards it. Um, and so, yeah, you may run into issues depending on your throughput, uh, for requests, for responses to that could be delayed. But yeah, that's a good, I mean, you can start this conversation, you kind of see what's going on. U, I'm trying to set up Oracle Terraform, but I've gotten conversion to work. Apple doesn't have it. Or you can just download Core ML models from the App Store yet, but you can download Quen Vision to iCloud. Oh, uh, interesting. Yeah, you can't download Core ML [snorts] models from the App Store. So, you, you can serve it from like a Redis or something, right? Like, uh, or some type of CDN, can't you? Like, that's probably what I would do is just like serve it from a CDN, and then, um, for people not eat up your bandwidth, you can just do, um, a check, a device check to make sure it's like an actual Apple device, not someone just hitting the endpoint, and then, um, once you do that, then you're, I think you're pretty much good, right? >> Yeah. Okay, got it. Uh, let's see. Okay, so what the chat would love Anthropic to help them create an all-seeing eye. I'm confused. What are you guys actually advocating for? Uh, I think, I think, um, Alex Finn kind of hit this on the head earlier, is that like America needs to stand up and support open source models. Like, we're both very, like American and very proud of like the country, and it's, it's amazing the innovation and the freedom that you have to speak. Like, I can speak about whatever I want. I don't have to say like, "I praise the government," whatever. It's like, if I don't like what the government's doing, I, I'll say it, you know? If I don't like what this company's doing, I'll say it, right? Like, that's the whole point. This is why we do live streams too, is because that freedom of speech, that like super important, and I think open models are one big part of that too, right? Like, we're the fact that we have to rely on a Chinese model that's like the frontier thing, and they're leading that whole system is like, it's kind of embarrassing, right? I, I think it's people are going to prefer to use those things that, you know, while they're open source and stuff, like it just doesn't really make any sense, right? Um, I can understand from a, "We want to keep everything protected," or if we expose too much secrets and everyone else can kind of copy them. So, I mean, it's a very complicated issue, but also we should be leading in that as well, right? So, I think tooling and all these different types of things, obviously these people are out to, um, you know, prioritize the things that they're working on that's going to generate them the most money because that's basically all they have, right? Like compute, the incoming people demand for meeting the stuff, and then all these like enterprise contracts and government contracts. Uh, but the government contracts come from us, like us taxpayers who give the government money, who, you know, like the Pentagon got their money from taxpayers, right? They're not just printing it out of thin air. And so, um, yeah, there's, there's, I mean, this can go in a lot of different directions, but I, I do believe like in freedom of speech, and I believe that, um, I feel like, like everything should have their checks, if you know what I mean. So, there shouldn't be too crazy as far as like one, like company having all the power. Like, it just doesn't make any sense. And then also like one government agency just having the all-seeing power, just is also just as scary, right? Um, which is actually why I really appreciated Apple's stance for security because like Apple said, "We're going to engineer these devices so that even if their data ends up in a data center that like they can't hand over the keys and then all of a sudden, you know, your customer data is like released." It's, it's just a standard security pattern, right? That just said, "Well, we don't want to have access to it. That's the customer's data that's secured via the secure enclave, right? Like, if you wipe the device, the key and everything for reading out those bits is, you can't do that, right? Like, you need the physical hardware all stacked together, uh, for for the device to read everything." So, um, yeah, very, very, very interesting like times that we're in. I think there's going to be a lot of, uh, interesting installations. Hey, finished the QMD skill. Cool. Yeah, we'll have to see what's going on. Uh, okay. So, um, cool. I agree. Grok 3 is a good start, but the Chinese models leaning open source is quite a bit of the problem. Yeah, I don't know. I think there's a lot of interesting innovations that are coming from China, which are fascinating. Like, they don't have the same resources that the US does. So, in essence, they're able to discover a lot more, like, or they're able to provide more focus to areas that are bottlenecks for them in terms of throughput, right? So, because they don't get the same throughput because they don't have GPUs, they're now able to tweak other parts of this really complicated system and then discover new techniques for like longer memory, uh, you know, compression, applying these other techniques that are kind of, kind of really out there. Uh, but then they're able to yield results, which is kind of wild, and it doesn't surprise me because this space, space is really, really large, and the use cases are now starting to reveal themselves the more that more people adopt AI and start using this stuff. So, I think this is a really cool step forward, uh, if you know what I mean. So, yeah.

Um, okay, cool. So, I'm going to go ahead and pop on out now and take care of things and head to the beach. I really appreciate everyone for tuning in. If you haven't had a chance to join the Discord, go ahead and take a look at that. Uh, if you can't do that, just go ahead and like and subscribe. Make sure you hit the thumbs up and share this with another friend. This really goes a long way. I've turned off advertising, and so the people who do support the Discord and all that stuff, you're really kind of helping this community build on forward. And I really appreciate you guys. We're just trying to grow this channel, uh, and get more cool stuff going on. Uh, and also, you know, working with, going to be working with some partnerships with different, uh, sponsors and different companies. Uh, that'll be like sponsoring the stream, which would be super helpful, and it'd be kind of nice. Um, that way I can kind of keep these, you know, turn off the ads because the thing I hate more than anything is like when I go to Twitch or something, like there's ads all the time. It's like, and they're not even good, too. So, it's like, I, I value people like you hanging out with me and hanging out with everyone else and kind of chatting about all the stuff that's going on in AI. So, we really appreciate you. Appreciate you. Appreciate it. Thanks for the live stream. Good content. Uh, love that about Hawaii. Don't. Yeah. I mean, like, it's amazing, right? So, it's beautiful outside. I got to go outside and go to the beach. It's been raining a lot because if you haven't been in Hawaii, it's been like super windy. It's still pretty windy right now. Uh, there's a lot of, there's been a lot of rain. So, like, now that there's some sunshine, like I'm not going to waste this moment and being inside right now. I'm just going to go outside and touch some grass. Uh, but this really helps the mind kind of heal and kind of get centered again. That way I can just come and straight up deliver value and not have to feel like I'm just burnt out, uh, inside all day. So, got to get some of that vitamin D. Got to get some, you know, get the dark skin going on. So, uh, ads open. I left the chair. [laughter] >> [gasps] >> Yeah, I appreciate everyone. I'm looking forward to the, the beach after coding, uh, in Hawaii in a couple months. That's, that's the setup right there. That's the setup. Uh, great stream, everyone. Sub for sure. Yeah. No, I appreciate that, man. I mean, it's, it's, it's free. This is what we do. And I appreciate everyone else who supports the channel. Um, got some really cool stuff coming up next. I'm really excited to kind of show you. And so, yeah, we got this guy, more, more. Stay tuned. Um, I'm playing around with some other stuff, and then I'll be able to, uh, after my Discord community kind of gives me some more feedback on my, uh, my memories and the dreams thing, I, I'll be able to share that skill publicly. I'm actually going to make like a whole repo plus like a, like similar thing to like the Claw Hub, but it's going to just be for my community and my people. Uh, that way it's kind of less, not like, I don't know, it's more specific to us, and, and if you're kind of vibing with the stream, it's just a really good place that, you know, that like I've spent a lot of time, my community members have spent a lot of time crafting these things, working with them together, and I feel like as a community, we can kind of have our own little hub, uh, that just be our own little, like section type of thing. So, I learned a lot, and everything I'll learn, I'm going to try to share back with you. Uh, so I appreciate that. So, uh, so yeah, the way that you can do that is literally, um, you know, like supporting the, the streams. You know, if you just go to the Discord, if you want to send me a DM, I can send you a link or something. Um, you know, [clears throat] I really appreciate everyone who's been able to do that. It actually does, it's what's really nice. It actually does help grow the business. So, that allows me to get more equipment and different things like this, like the Open Claw thing, the Mac Studios, um, you know, the editing, the high, you know, high quality stuff that I really try to do. I also have the fortune of being in Silicon Valley, which allows me to get access to these different, you know, events and stuff. So, I, you know, I have a whole IRL setup, which this is actually a whole part of the whole system. So, I'll be able to walk around with this camera, and you've seen me doing some of those tests live already. And so, I want to bring more of those types of things in because, uh, I want to bump into, like, literally being in San Francisco, we bumped into the founder of Factory AI while we were hanging out with AJ and also hanging out with Maddie, you know, in a beautiful day in San Francisco, you know, be out here in Hawaii as well doing some stuff outside. So, I want to, I want to do more of those types of things. And so, yeah, if you want to send a DM or something, just let me know, and then we'll link up. So, yeah, I got some more coming. So, for sure. Um, thank you so much for becoming a member as well. I really do appreciate that. This is really, really helpful. Uh, did you set up Mission Control yet? Mine is, um, wondering how to get it properly set up like Alex Finn did. Uh, I have not set up a Mission Control, and I'm going to experiment on the stream coming up where I'm going to try to look at Notion, and I'm also going to try to see if I can build my own system. The first part of it is trying to see if I can tap into Notion because Notion already has a lot of the apps pre-built, right? That has views for Kanban boards. It already has databases. It already has these types of things. Those things sync to my system, and they can also be displayed through through my lock screen as widgets. So, Notion seems like an interesting thing. I already have a lot of stuff in Notion anyways. So, it'll just be about putting stuff in there that could be really interesting. Uh, the other part of it is making an iOS app because I want to basically replace Siri. So, that's another type of thing that I'm going to try to get into. Try to see if I can have a Siri app basically that is going to sit in my house. Uh, and I'm also going to try to get this latest model from Quen text-to-speech and see if I can get that loaded up on my DJX Spark. So, that'll be like my at-home Siri. And, um, it also be available for my friends. So, the I want to get that working through the HomePods. There is like a SiriKit. I really don't know all the specific details, but I, I mean, this was a while back when I was working at this fruit company, and I'm not sure what's public and what's not. This is part of the reason why I don't do a lot of streams on iOS stuff because I don't really want to accidentally disclose things. So, uh, I will like use everything, uh, publicly available to try to look at stuff and try to make have the agents write the code so that I'm not writing the code, if you know what I mean. So, that's what's up. What about in Sydney? Just use a look file as well. Yeah, I'm sitting pretty cool. I think the syncing part is what I want, you know? So, when I write stuff in, I want it to show up on my phone. So, that's kind of what's nice about Telegram is like has such a low signal. It works offline. Like, when it comes back online with low signal, you know, Telegram will hit the gateway and then send that off to the agent. So, that's kind of the way I'm thinking about Notion here, that like I don't have to have the app that's running all the time. Whenever my phone connects back, you know, Notion's already kind of a known thing. It's battle-tested already, so it's, um, it's a pretty good gateway, and they already have good stuff for managing things overall. So, uh, do you know how to set it up so the agents can talk to each other, have meetings? That's probably what I'm going to get to in the next stream. So, uh, that's what's up. Uh, but I appreciate everyone. Would love to be SF more. Uh, you give me the feeling of being close to it at least. Uh, much love from Germany. Hey, thanks, man. I really appreciate that. That's really, really cool. Uh, yeah, that's really, really awesome. I appreciate that. Yeah, I think whatever I could do is really cool. So, we'll be there as well. Um, do I have concerns about Telegram logging chats? I do and I don't, but like, I'm not super concerned because it's not anything super private, per se. Um, and that's also something that like, if you are concerned, you can make your own app because all you have to do is just talk to the gateway directly via your own means. So, you can use iMessage if you want, and you can kind of connect to it that way as well. So, that's what's up.

All right, y'all. I got to head out cuz the beach weather is so good. [laughter] All right, y'all. Peace.