[00:00] Hello, guys. Well, at least you know that I'm real, seeing as my computer crashed. How's it going, everybody?
[00:13] How are you guys doing? I crashed. Thank you so much for joining. Thank you so much, everybody, for waking up
[00:25] or being up at 2 a.m. I'm sorry. It's very difficult to accommodate all time zones. It is currently 10 p.m. for me. Okay, so I have a few people from U.S.
[00:37] Okay, so, hey, Richard. It's been a while. 7 a.m. East Coast time. Sorry, West Coast time. West Coast time. It's 10 a.m. East Coast time. Michigan, hello.
[00:51] Hermes hacked her camera. Don't say that. Don't jinx it. I have actually been playing with, like, hardware. so it's gonna be my next video okay i'm like i just gotta show you guys this is very exciting
[01:03] um i'm using a pi and then connecting it running local models off it and also like using the esp32 as well and it's actually able to like control my camera and stuff so
[01:15] it's very exciting i'm excited to show you guys 5 a.m oh my goodness thank you so much for joining hello i didn't even have coffee yet
[01:27] I'm trying to hang your desk, okay? All right, let's get going. So what are we doing today? We're going to be talking about, that's a great question. Great question. Yes, I will be talking about Hermes setup
[01:41] because I've made a couple videos about it. Let me know, comment Hermes if you've seen any of my videos that I made about Hermes. But I feel like I didn't really do it justice. And we do have a workshop that's currently enrolling right now.
[01:53] So this workshop, I'm actually going to be teaching you how to build all these things too so I really want to like show you guys what it is that we have I've spent like months building this up and I'm very proud of it and I'm also like um because
[02:07] I'm connecting it to stuff like the aura ring so thank you guys again for people who suggested that I get the aura ring um connecting to that and also using like other like hardware and stuff like that so experimenting using like really small uh devices and then being able to run Hermes
[02:23] and then also run different local models too. That's what I'm experimenting with. And it's actually really cool. Like, okay, getting ahead of myself. Really cool, really cool. Hermes bag, no.
[02:35] No, I don't have a Hermes bag, I'm afraid. Hermes, yes, nice. Okay, some of you guys have seen my Hermes video, okay? Great, some of you guys have not. So I want to show you guys what I have. Okay, so I want to show you guys.
[02:48] Let me show my screen. Okay. One second. Hold on. Let me share my screen.
[03:02] Okay, there we go. That should work. Great. For me, it's live stream, as you guys can see. Okay, cool. So I want to show you guys a couple demos first. So the first one is Taco Bot.
[03:14] So live demos, guys. I hope it works. Oh, my gosh. It's a live demo. So this is, like, actually our Discord. for us our internal team we use discord for everything we use slack for the external team
[03:28] and stuff but I want to show you guys like taco bot um actually let me start off so we use this a lot for work so I can go like at taco bot remind me in five minutes to move on to live bot
[03:46] okay so it should be listed that reminder for us and it can do certain things like for example i can go to our work updates for example and then i can say something like at taco bot
[04:03] uh what is everybody working on right now and it should be able to do that and let's see okay so you can see that it's connecting to
[04:23] notion so we have our meetings and notion as well so it's connecting there our meeting notes and you can see what's over there it can also read all of discord um calendar and a lot of other
[04:36] sources like GitHub as well, so it's able to gather what everybody on the team is doing. So let that run for a bit. Okay, so yeah, and it's able to schedule reminders
[04:48] for us. Let's go back and stare at this for a bit. Okay, cool. So based on the latest team meeting notes,
[05:00] here's what we're currently doing. So set up guides for the Hermes workshop, workshop calendar and life bot access rollout this is what Jovi is doing Jonathan and Cotter are doing this Ken is doing this and the whole team is prepping for our
[05:12] Hermes workshop launch actually have you guys seen the are you guys on the newsletter comment workshop if you are registered for the Hermes workshop I'm very excited to see you guys there because we're going to actually I'm going to be
[05:24] like teaching you how to build all of these systems during a workshop so comment workshop if you are going to be there um another thing that I can do here is say for example I have we have like this YouTube
[05:39] trend tool right like or let's see let's see right here okay um I can ask you to like create a process doc and how this product works and it's able to like go through and actually explain how
[05:53] all our products work and things like that um and all of it is actually being stored in obsidian So I know some of you guys have been watching the Obsidian video, so I just want to show you, like, what that looks like in Obsidian as well.
[06:07] Let's go to Obsidian. Yeah, so everything gets stored here in Obsidian. Like here, YouTube topic I'm doing, and it would actually just, like, have all of these process docs.
[06:19] So then every time you need to have documentation for things, you're able to very easily document it. For any business owners out there or people who work in teams, this is like it is honestly so useful to be able to have this bot that can tell you and document
[06:33] everything that you're doing uh they can generate reports for you as well so we have weekly reports that are generated um through taco bar as well so you don't have to like go and make your own dashboards own reports anymore yeah pretty amazing right all of this is being run by a hermes agent
[06:47] um let me go back no wrong one this one cool yeah so all of this is being generated uh by a hermes agent so it's actually
[07:01] one of the only that is one of the profiles that we have on my on my hermes agent come and talk about if you get the vibe why that is useful um did you guys do you think do you guys think like
[07:15] something like this would be useful for you like have you implemented something like this before hey okay so you guys are here from the workshop amazing thank you so much i'm very excited to see you guys there i do not have the funds for rolling the workshop but it sounds exciting
[07:31] no problem i also have lots of free resources that you can check out from my videos as well the workshop is for people who want to be able to build all of this within a span of two hours because it took me like months and months to figure out how to build it right so
[07:45] for those of you who go to the workshop it's going to be like a two-hour sprint and we're going to get all of this done talk about talk about nice amazing uh is this workshop suitable for beginners yes it is it is completely beginner friendly um i do get your point this is something
[08:02] definitely is where i need to build up right like yeah like i will literally show you so this is only one of the profiles that i have um and i want to show you like the others i have quite a few profiles but the other profile that I use a lot um is called life bot so this one is life bot
[08:19] oh by the way I'm actually just gonna put this here if you guys want to check out the workshop um enrollment is open now so enrollment for Hermes workshop here so do check it out if you are interested
[08:35] and doing that let me just pin that comment as well pin message okay some questions who is the workshop for i just joined workshop is for people who want to
[08:50] build the things i'm going to be showing you right now and do it in two hours as opposed to like be like me and spend like months doing it that's for the workshop as well completely beginner friendly as well if you wish if you wish um if you're not free during the workshop time do you record it
[09:05] Yes, everything is recorded as well, and you also get resources and ideas on how to build step-by-step guides on how to build things as well. So even if you, not only will we be building this, I will be building it, you can also follow along, build it if you care out there.
[09:19] It is recorded, and we also have full-on checklists and guides that you can look at yourself and then build it too. How is it different from OpenClaw?
[09:32] So Kermit is actually pretty similar to OpenClaw, but in terms of premise, but I find that it's easier to build around. That's an interesting thing. Like, OpenClaw is really cool. It's very magical when you first use it. But I found that after about, like, a month or so,
[09:44] it started to get clunkier and clunkier. Things started breaking, maybe because they have new updates being done. But with Hermes, when something is actually built, it doesn't just break. So, for example, TacoBot, I've been using for, like, months now. And so has LifeBot.
[09:57] Speaking of which, let me show you guys LifeBot. I'm also going to be going into more detail about, like, my building process a little bit later in the live stream as well. So just want to show you guys the demos first because I'm pretty proud of them. Okay, so this is, like, for example, it actually notes down everything.
[10:13] Like, I track everything using LiveBot, like, the stuff that I'm building, like, what I'm working on. I also track, like, how much food I'm eating and things like that. For example, I had an egg tart and half sandwiches today.
[10:25] So, yeah, I'm able to do that. And I'm able to ask you questions like, let's see, how is my progress for today compared, like, how is my work progress today, for example?
[10:50] it should actually be like not that good I think because I don't think I logged too much time but let's see um yeah so I use it to just like answer okay there you go I use it to just ask you a lot of
[11:12] questions um because it has like it's based upon my actual data right which means that it's able it gives me very very specific and specialized advice if you ever have like you know productivity people like tell you oh you should use this time you should do this you should do that
[11:26] or like i was trying to do fasting for example oftentimes like it's not tailored towards you specifically so then you end up not being able to do it but because lifebot is built using like your specific data built using hermes that's how it's able to make sure it's giving you like very
[11:40] specific advice and it's i've been using this for about two months now and it's freaking amazing So, for example, it shows that my Pomodoro log 2 is for one session. My health metrics are stale right now.
[11:52] My health metrics, I update this every night. So it hasn't come in yet. It's only 10 p.m. And it also says that here's the things that I've done, like review live stream slides and test all the demos end-to-end before going live.
[12:04] You know, which I did. And, yeah, right now we are running the 10 p.m. live stream active now, as it knows. And it tells me, like, what my work in progress is. um essential analysis log volume this is well below your historical median so it's able to
[12:16] compare that um executive execution shape today was not a built or deep work day so it knows like the type of days that i'm having it's able to give me like the best advice for that specific day like it's very subtle sometimes i feel like i'm not able to like explain it do it justice
[12:32] but because it's so tailored towards me it's able to give me very very tailored advice like i can also ask the questions like how do i improve my productivity overall and log more deep work hours, right?
[12:48] Like I can ask you something like that.
[13:01] Good morning. So excited for the workshop. Yes. I'm really excited to show you guys doing the workshop. Like, I think you're being blown away how much you can actually do, especially with the setup that I'm going to show you guys how to do it.
[13:16] Like, you're able to build things so quickly now if you know how to do it. It's pretty crazy. Okay. Let's see. Ada's reading is going to the skills right now.
[13:32] Have I used RunPod? Yes, I used RunPod. but use it mostly to rent GPUs. That's what I've been doing with Rampod.
[13:46] Once I have Hermes plus Hermes bot set up in my MacBook Pro, I was on the 18-gig unit of Hermon. How do I choose LLMs? How do I choose different LLMs once I get a computer with more memory? Honestly, 18-gig is completely enough, especially if you're using cloud models.
[13:59] Vacancy is crazy. Yep. I also do have a VPN on right now, so I think that's not helping. Okay, so see how it's able to give you very tailored advice, like enter your first timer by 1pm. Basically, my number one lever for me specifically is that if I'm able to start working by 1pm, I'm able to get a lot more work in. And this is so true. Like every hour past 1pm costs you 20 to 25 minutes of total daily focus. So the rule is that lock can at least 20 minute timer before 1pm every day, even if it's just planning or like prep.
[14:33] This has helped so much. A long time duration for 20, 25 minutes. I am someone who is incapable of focusing for long periods of time. So if I do like an hour, try to work for an hour, that's just not going to work. I'm just going to give up. Like literally, I just give up.
[14:45] So LifeBot was able to figure out like I need to be doing 20 to 25 minute Pomodoro sessions for it to work for me. Using 10-minute tasks, but just to protect scripting. So depending on the type of task that I do as well, there's a different percentage of
[15:00] completion rates. So a hack that I've been doing is that for me, like scripting is really hard, right? Like it takes up like a lot of my mental energy. So I would do something like do some tasks first to kind of ease into scripting and then
[15:14] always like making sure that I don't stop working immediately after a scripting session. So it's like these very subtle but little tweaks that you can do, little hacks that you can do that's very specific to me that has really genuinely like it changes the way
[15:27] that I work. And I feel so much more productive. and now we're able to get so much done as well. So et cetera, et cetera. I think we'll do all this. And all of this data, like how I was able to get all these data, I'm going to show you guys as well.
[15:40] It is – where's my little guys? Oops. Give me one second. I had to restart my computer. So let me show you my little app.
[16:00] speaking so I am able to do this because of these little guys over here so this one is I'm able to
[16:16] have the checklist of everything that I'm doing and then here is like I have the pomodoro and every time I log time into this I can do like one minute tests for example all of this and when I
[16:28] check things off, it all gets logged into Obsidian. So let me show you in Obsidian. This is such a game changer. Honestly, such a game changer. So my typewriter, I'm able to log
[16:41] like every single day that I'm doing. And the more days that I have, the more data LifeBot is able to get, like Hermes is able to get. Again, this is all running off Hermes right now. And also with my workouts so there's just like workout stuff and my pomodoros too so all my pomodoro logs that i've
[16:59] been doing the more data that it gets and the commentary that it gets the better that it becomes so over time since i've been using it for about like two months now it has been it's gotten so
[17:11] good at giving me very very good feedback so genuinely highly recommend doing that um yeah so So that is a little demo of what you can do with Hermes.
[17:24] And I'll tell you guys some other stuff I'm doing with Hermes, but I don't want to just have this only be a demo. But yeah, do you guys have any questions so far
[17:36] about what it looks like of what it is Let me see You guys have any questions Avocado cute and helpful to stay focused Indeed it is
[17:50] I signed up with the screen refresh before I could look at the other offer that appeared. I did email you. If you email us, we will get back to you. Please give us a couple hours. We should be able to get back to you.
[18:03] Thank you for emailing us. So yeah, we also are selling the live bot completely. like you can just get it all so that's what it works anyways do you really use lm successfully i mean all of this is based on hermes which is using lm so what is hermes good question hermes
[18:19] is an agent harness that allows you to build custom agents that you can do things like talk about which i just showed you life bot that which i just showed you so these are all built using hermes and let me actually show you let's dissect it a little bit okay so we saw talk about earlier
[18:34] um oh yeah i got really excited so what are we going to be covering today so i guess i showed you guys the demos um so we're going to be talking about taco box profile and also life box profile and then i want to show you the stack underneath so what are the tools that i use in order to build
[18:50] this as well as the step-by-step process that i use to build something like this because before to build me like this this was taking me like weeks probably to like get this done but with like a certain I do like a certain sequence of steps that I do I've gotten it to a point in
[19:05] which I can get it done um probably like half a day like and during the during the workshop I'm going to show you how to do this like I've gotten it the way I can build using home use now I can like get entire things entire projects done within like 10-20 minutes it's crazy uh and it totally
[19:22] works on like other devices and things like that as well so it's like I perfected the way at least Hermia, perfected the way to be able to do that. And then I want to talk about some other build ideas, as well as some ideas that you can build using Hermia as well. Okay, so Talkabout. So,
[19:39] for each Hermia agent, it requires certain parts. You can think of it kind of like Lego, right? Like you have your Hermia agent, and you can customize it depending on how it is that you want to do. So, for Talkabout, for example, we can see that it lives on Discord, right? So,
[19:55] So TacoBot lives on Discord. And the model that I'm using right now is using Gemini 3.8 Flash because it's really fast. But sometimes I do want to have it completely local, which I would use the QEM 2.6 35-bit model.
[20:09] And the home for TacoBot is on the Mac Studio that I have here. You don't need to have a Mac Studio. You can run it in a lot of different places, including like a VPS on your computer, a lot of different things. But I happen to just have it on a Mac Studio.
[20:22] And then you need to give it your own data access. For me, I've given it data access to Notion, GitHub, calendar meetings, recordings, and Discord threads. That's why it's able to answer questions. It's able to answer questions that I ask it and is also able to store that information as well.
[20:37] So in the memory, it has what's called Honto shared memory, so it's able to have specific memory. I'm not going to go into too much detail about that. But it also has long-term memory, which is on Obsidian, which I showed you guys earlier.
[20:49] Any questions about Talkabout, how it's built? Will you share hardware requirements, recommendations, prior to workshop?
[21:01] Yes, we will. But honestly, I would be shocked if you don't have the hardware requirements. The only thing I can think of that would make you unable to do it is if you don't have a laptop at all. If you only have a phone, I think that's going to be hard.
[21:14] But pretty much even if you have a Raspberry Pi, that would be fine as hardware. like really with hardware i think people don't realize how accessible it actually is now if you have like four gigabytes of ram that's enough for hardware yeah you don't get to have as local
[21:30] models but you can always use cloud models um i can i'm using grokbox a very similar kind of box how do you compare both things like i think they're completely different right they're very different sorts of things with hermes it's the whole point of hermes like why is it that we use
[21:45] Hermes as opposed to something else is because it allows you to switch out models. You're not like bound to like Grok, for example. You're not bound to OpenAI, for example. You're able to switch out models and you can also make it completely local too. So sometimes there's things that you maybe
[21:59] don't want these tech companies to have the information that you have, right? So you can use completely local models and have Hermes running locally too. So none of this information ever gets out. So powerful, especially if you're in a team and you don't want, you know, your team
[22:13] secrets to be leaking out um workshop yes i'm excited to see you guys so what amount of memory would you recommend for local models i think you have a decent local model 16 gigs is i would say
[22:29] you can get a very very decent model with 16 gigs 8 gigs i think it's okay like you can have a decent conversation with it um you know like i you guys want to guess what do you think is the
[22:42] smallest model that you can run that is able to run a model. Like, smallest amount of RAM available to run a model. I'm just curious if you guys can guess. A little hint, my ESP32 is able to run a model.
[22:58] Like, this tiny little thing over here is able to run a model. Thank you, guys.
[23:12] 3.5.
[23:30] Yeah. Yeah, 3.5. Exactly. So the ones I think, I believe it is three megabytes. It was able to run a model that is three megabytes. And you're able to have, like, this one you can't really have a conversation with,
[23:46] but it's able to generate stories. These are called, like, tiny stories models. And, yeah, like, that's it. This is how, like, how small of a device you can actually use in order to run models. So don't be worried that your device is not good enough to run Hermes or run models.
[24:01] Yeah? Good job. Yay! Good job. Okay. Okay, so I already showed you guys LifeBot, so that's the way that LifeBot works.
[24:15] If you guys have seen my Obsidian video, LifeBot is heavily dependent on Obsidian because that is where it gathers all of that data and stores it as an AI database in Obsidian. And LifeBot, which is a Hermes agent, is able to access that directly.
[24:30] So because of that database, very, very high-quality data, that is what makes LifeBot really, really good. and here are the specs for Lifebox.
[24:45] So communication-wise, it's on Telegram, as I have just shown you. The model that I use, I currently am using DeepCity for Pro, but I also sometimes use GPD 5.6 Terra, depending on, I don't know, the vibe that I feel like that day,
[25:01] or sometimes there's like free credits for certain things, I would use that. But they're both really good, and if I want to use a local model, my favorite model is still the QEN 3.6 35B. I honestly think it's one of, like, the best models to be able to run locally because, yeah, like, it's just good enough where you don't need, like, a massive machine to be able to run it, but it's able to pretty much do everything that you need.
[25:22] The home is also on the Mac Studio. Again, it doesn't need to be. It can be on any device. Like, if you have a laptop, chances are you're going to be able to run it completely fine. Data access, as I said, Pomodoro, Typewriter, Apple Health, Oura Ring, and food tracking and exercise logs.
[25:37] Like, I have this all stored in the AI database. And in terms of memory, the same setup as TacoBot. So Hancho shared memory, so it's able to get information, as well as long-term Obsidian memory.
[25:49] Any questions about LifeBot? Question. Obsidian is more of an archive-slash-library than persistent memory.
[26:03] How do you deal with outdated or superseded material in Obsidian? Great question. so the short answer is that I make sure that what is being written is of a high quality for example if I'm doing logs and stuff right it's not going to be information that's going to become irrelevant
[26:18] because it's very very well formatted the long answer is I use something called the LRM wiki so it's able to prune that information over time it actually does it automatically workshop yes see I think I just showed you right lifebot um and and taco bot like
[26:36] You guys will be building this yourself on your computer or whatever device it is that you're choosing, a GPS, whatever machine. Yes, you will have your very own versions of, you can build these things.
[26:51] Let's see. Which demo model? Which demo model? Not sure I understand the question. I do have an entropic clause description. Can I use it with Hermes?
[27:03] You can use your cloud code with Hermes, yes. That's fine. Okay. Next slide. Okay, so make sense, right?
[27:15] Very cool. Call my life spot if you understand why life spot is amazing and useful and important.
[27:27] If you get a life spot, if you get it. If you get it, if you get it. If you get it, if you get it. yes yes okay I'm really glad that you guys get it like lifebox single-handedly has really really
[27:44] changed how productive I am and not just that like also like tracking stuff um I'm the kind of person that's like I always wanted to track my exercise I wanted to track like my food intake and all these things but I'm like way too lazy I can't handle it actually having to track it myself so I
[27:59] just got lifebox to do all of it for me someone said a wife spot no you can try you can try wife bought. I don't know. I cannot confirm or deny if that is good or not. Okay, let's move on.
[28:15] So let's talk about the actual tools that I use. Okay, so stack underneath all of the home use agents that I built. So obviously, the first one is having home use agents, which is the home base. So it has a desktop app, a terminal or dashboard. So you can have all these different things.
[28:31] Let me actually show you... I'll try to do this without crashing the system. Okay, I might end up having to crash it.
[28:44] Okay, I'm going to try... I do... I'm going to actually log into my Maps feeder right now, and I want to show you the home use itself, what it actually looks like.
[28:59] Hopefully it lets me do that. Okay, ooh. Okay. I think we're being a bit laggy because my laptop might not be able to handle this right
[29:24] now. Okay, I'm going to try. If it lags, then alas. Wait, it's not going to work.
[29:39] Okay. Okay, so this is me logging in to my Mac Studio, right, where a lot of these Hermes agents are running. And you can see that this is Hermes over here.
[29:51] um yeah it's really slow because i'm trying to live stream at the same time but this is the hermes desktop app and it's really easy this is what i mean you don't even need to know how to code like you can say like install lifebox for me i'm not going to run this right now just because
[30:05] you know we're live right now but this is what it looks like and you can have like different agents that you can talk to directly um as well so there's like different sessions that you can talk to directly so that's one way to access it you can also access it through terminal
[30:19] So for example, you can go in terminal over here and say something like, oops, you can also do say, um, live chat.
[30:41] And that loads through her music as well. So I can say, you can see that has Gemini 3.8 Flash. You can be like, hi. Yeah, and it's able to talk to you.
[30:58] So there's like, this is what it looks like. Just kind of show you guys what that looks like. That is what it looks like. So you can do it through your terminal using code, but you can also do it using a desktop app.
[31:10] So either way, if you know how to code, you don't know how to code, you can do it both ways. So it's actually really, really accessible. Okay, let's see if anybody has any questions. does anybody have any questions about what Hermes looks like?
[31:24] How many of you guys have actually tried running a Hermes agent? Just write Hermes if you've actually run your own Hermes agent. Just for me to kind of get a vibe.
[31:36] Let me just also move, go back to the start. Okay, cool. How many of you guys have run, you've done, okay, nice. A lot of you guys have done it, right?
[31:48] Okay. Great. So a lot of you have tried. So for those of you that have tried, who haven't tried, do you feel like what you've built has been useful for you? So far, for those of you who haven't tried, I hope that kind of shows you like it's really
[32:01] not super scary, intimidating to actually get started using Hermes. There's like, they have a full desktop app now. So you don't even need to know how to code, which is pretty cool, right? I don't know how to create more than one agent slash bot in Hermes.
[32:14] You can make multiple profiles. That's what they're called. multiple profiles. So useful. I have a hernias, but I don't know how to set up the different agents you got set up. Hopefully, you can learn that from you. Yeah.
[32:27] So I have a lot of free content on this where you can go in the workshop where I'll actually be taking through this with you like step by step. But really, I promise you, it is not as difficult as you think it is once you actually get the hang of it.
[32:43] I don't have API key, so I can't use it a lot. that is fair or Lama versus Lama CPP for Hermes great question yeah so or Lama is actually built on top of Lama CPP
[32:55] so it's an easier way for you to access local models if you use O-Lama however if you want to have more control and also be faster you would just use Lama CPP directly I use Lama CPP directly
[33:07] you do need to know like you gotta do a little bit of code if you're going to use Lama CPP so you know it's not that hard but you do need to know a little bit of code So if you can, I would use Lama CPC. But if you want to just get it, like, really fast and runny, you can use Lama.
[33:20] That's the distinction. Okay. All right. So, anyways, so what do you need to actually build what I just showed you, right? These things I just showed you. So, obviously, first you need to have a her newsagent.
[33:33] It's free. Download it. Then you need AI chat. So with AI chat, what I mean is I like to use cloud or open AI in order to think through what I'm going to be building first. I'll show you guys in a little bit what I mean by that.
[33:47] But I actually always want to, like, think through what I'm building first with AI before I actually go and execute it. You also would need an AI coding agent. I mean, you don't need a coding agent, but it does make things a lot faster if you have an AI coding agent,
[33:59] if you're using Codex, Cloud Code, or you can even use OpenCode, the open source version, because this can help you execute a lot faster if you're using an AI coding agent. Another thing that you need is an Obsidian AI database.
[34:11] So, Clearable Record, which I just showed you earlier, of past build specs, like a lot of information you can sort into your Obsidian AI database. And then this one is kind of optional, but I think it's really helpful. It's an Obsidian LM Wiki.
[34:24] How many of you guys have heard about LM Wiki before? Comment LM Wiki if you have heard about it before. Quite simply, an LM Wiki is a managed library of different sources that you can query,
[34:39] and it's fully managed by AI. So it's like you're able to take notes and then the AI is able to go through it, scan it, get rid of stale stuff, update it over time. You can also query and ask your questions too.
[34:51] So I kind of want to show you guys, I have a LLM wiki that's dedicated to Hermes actually because every time I find something new that I think is interesting, I would put it into my LLM wiki so that when I want to build using it later,
[35:04] I can ask my wiki bot who accesses my LLM wiki to be able to give me information about it. For example, I'm just giving you an example. I'm like, maybe I come across this really cool holographic memory. Wow, so interesting.
[35:17] What is holographic memory? Who knows? And it like what this In Chinese what does that mean And I can do something like I hope this works oh please work yeah so all I have to do is put the link over here through my wikibot again
[35:35] wikibot is also a Hermes agent so see how flexible Hermes agents are um they also are Hermes agents let's wait a little bit hopefully it's able to digest the information that I give it
[35:50] LMWiki. Okay, great. Some of you guys know. Nice! A lot of you guys have actually done LMWikis. That's pretty cool. Please! Why is it being so slow?
[36:06] Okay, well, I'm not, like, crashing it. Let's answer some questions. I know. Live demos, you know? Live demos. I mean, it's actually worked thus far. So, if this doesn't work, I'm not going to be super shy.
[36:18] I wouldn't even be mad because honestly it's been pretty decent up until now. As you see, I was literally testing it at like 6.42 p.m. and it was fine. So let's let's move on.
[36:34] Okay, let's see if it's going to work or not. I'm going to answer some questions. Oh, man. Obviously it's going to not work right now. Okay, I'm going to try again.
[36:46] I'm going to try to query it. Tell me about how to make a comp on board. Oh, okay. No! Okay, I'm sorry.
[36:58] It was just being slow because... Darn it. It's okay. Let's answer some more questions.
[37:12] Don't worry. It happened to be my presentation yesterday, right? Like, obviously, if it's going to fail, it has to do it. It has to do it during the live demo. always, always. Sure, it's a live log as I'm working on LLM Wiki.
[37:27] I'm not going to do that right now because I got an SSH into my match to do, and I don't want to crash everything because I'm live streaming right now. So you're going to have to trust that. Hey, see, my blog is doing it right now. Actually, you can just read here. Yeah.
[37:43] You are brave just for trying live demos, right? I've been trying to do live demos the entire time. So thank you. I feel like I'm being acknowledged for how brave I am right now. Thank you.
[37:55] You have issues too. I have issues every day, like constantly. Where do you use that situation to your max to do? I just use, oh, I use Tailscale. Yes.
[38:10] What is the cost of ingesting data in LLM-Wiki in terms of token usage? Great question. It depends on the model that you're using. If you're using a local model, it's free.
[38:22] Any good resources to find the models that work with 1D to 2D group DQs with Olamo? You can just ask an AI to do that. Just ask what works.
[38:34] You know, that works. Hey, it actually worked. Wow. Isn't that amazing that it actually worked? Okay. So, let's see.
[38:46] seriously. About holographic memory. So holographic is experimental local first persistent memory engine created by agents. Its main features are blah blah blah. So it tells you like and then it also tells me how to create a dedicated combo on board. So blah blah blah all these different things.
[39:00] Okay so what does it actually look like? If I go to my obsidian I can actually show you what it looks like. What's my little this version of my LLM wiki looks like. please work please
[39:16] okay sitting over here um sit with my wiki okay whoa
[39:32] okay queries concepts so I have a lot of concepts that are here raw okay so here are the raw
[39:49] things I ingested I think it's because I interrupted it earlier due to my impatience that you don't actually see the um I'm just going to try this again just because I do want it to ingest.
[40:05] So it should ingest. So let me just try this again. It's going to ingest it at some point. But you can see, like, here's the things that, all the raw things that it stores. So it would actually document all of this, and then it's able to make a bunch of connections based upon these.
[40:21] So this is what the LRM rookie actually looks like. So I'm not going to go into way too much detail right now, just because not that much time. Oh, wow, we're at 1047. Wow, okay. yeah so then um it's able to ingest it and then it's also able to query it that's why it's able
[40:34] to tell me like oh here's how you can build something like a Kanban board right um and it's able to cross-reference that with my actual Hermes build it can tell me exact steps for doing things so that's the other tool that I like to use when I'm building um yes let me go back to
[40:52] the slides I get so excited when I talk about the builds. Okay, cool.
[41:05] So that's what I do this. It's currently extracting and ingesting all of this into the LMWiki. But let's go back to the slides first. So these are the things that I use in order to do my builds, right?
[41:18] Does anybody have any questions about any of these tools that I just described before I talk about how I use these tools to build it? open obsidian stuff about my life no
[41:36] obsidian versus our wiki comparison why need both obsidian is a tool our wiki is the implementation of an llm managed uh wikipedia page it's not wikipedia page like what they call like wiki
[41:50] like wiki resource you're just you're using obsidian in order to implement an llm wiki and to visualize the LRM wiki. So completely different things.
[42:08] Does LRM wiki work the same way Hermes does? So I actually used Hermes to build my LRM wiki. My LRM wiki is managed by my Hermes. Everything I'm showing you guys, because this is a Hermes livestream,
[42:20] like everything I'm showing you guys, I built using Hermes. Yes. Pretty cool, right? I'm telling you, Hermes is pretty magical, in my opinion. Okay, so it says that it has been captured, so it's going to show up in Obsidian now.
[42:37] So let's actually see if it shows up in Obsidian. I want to show you guys real quick before I move on. There you go, see? It showed up in my Obsidian now.
[42:53] great um okay let's go back i want to show you guys the actual process i built this and i think this part is really important so i don't want to rush that uh okay yes so how do i actually build
[43:08] this so from idea to running the agent right so what i do is like i have a i basically collect a bunch of things i want to build what i think is interesting for my um for my home is built right
[43:20] because you can customize and build so many different things with it. So I collect it, and I use my LM wiki in order to send it links of, like, cool things that I find so that I'm able to store that in that wiki. It's filed by wiki bot, which is managed by Hermes.
[43:32] When the time comes, I'm like, I actually really want to build this thing, I would query the LM wiki like I did earlier, say, like, I want to build stuff using the Kanban board. It would actually tell me, like, step-by-step how to do it. So in order to implement this, I would then go to a chat, like Cloud or OpenAI,
[43:48] and then I would come up with a runbook. So I can't actually show you my cloud right now because I don't have a VPN turned on because I'm afraid I'm going to kill my stream right now.
[44:00] So I'm going to show you what the runbook looks like though. I work on this runbook with cloud. Where is it?
[44:13] Please show up. Where'd you go, runbook? okay okay yes it is not beautiful so sorry about that you don't have to read it like it's just the
[44:28] concept of it so i basically come up with this runbook using cloud based upon information i have in my in my lrm wiki and then it would come up with like so this is like literally one of the builds that i was doing right it's called the hermes expansion roadmap and it would come up
[44:42] with different phases this is when i was building taco bot which is the lr team bot um and then phase B, which is LifeBot, phase C, retry, patterns, blah, blah, blah. So it literally has this runbook. And then what I do, which is, this is the
[44:55] part, okay, are you guys ready? This is like the magical part, okay? After I build this runbook, I would go and just use a coding agent and just give it to the coding agent and ask him to build
[45:07] it for me. That's it. It just does it. That's what you do. Just open Cloud Code or OpenCode or Codex, whatever you want to use, and then just give it like I just go and type in like I want to run this runbook right I would just give it like
[45:21] phase a like this is what I want to do and just give it to your coding agent and it's able to implement this it's not crazy so in some ways like what is the most like useful thing in terms of what you're building is the actual runbook itself once you actually have the runbook
[45:36] in terms of what it is that you want to build and you figure out what it is that you want to build the rest of it you can just hand it off to a coding agent so what I said here the slow step is the point. So put the effort into figuring out the runbook up front even if it takes days or weeks
[45:49] so you're not spending even more time fixing the build afterwards. If you don't spend time on your runbook then you're not going to be building the right things and then you're going to be very sad as you're trying to fix things. So this part is the most important part. I was telling you earlier like why is it that I can
[46:01] like build this entire thing on Lightstream and I can like during our workshop I can do this in two hours but it took me like months to actually get to this point is because I was trying to figure out what the runbook is supposed to be but once I figured out how to do it the execution step
[46:13] is so fast for using coding agents. Okay, any questions? I think this is like legit, like probably the most important part, like the process of execution of building your homey
[46:25] is this. So any questions?
[46:38] Why does Hermie sometimes give me answers that are trashy? Why does Hermie sometimes hallucinate? It can be a few reasons. Maybe it's because you're not using a good model. It could also be because you're not prompting her needs. So you're not prompting it, getting it the right prompts.
[46:53] That could also be the case. That's one of the reasons why you want your runbook to be really good. Because if you are, that's probably like two of the major reasons why that could be the case. Do you read it?
[47:05] Read the runbooks? I do read it. I skim through it, like just to make sure it's okay. But as I'm building it with Claude, who we're opening out, as I'm building it, I would be, like, asking you to just go back and forth.
[47:17] Like, I try to understand everything that is actually building. So I do try my best to actually understand what is building and not just, like, oh, whatever, like, do whatever you want, you know. I do try my best to actually understand it. Yeah. I don't read it, like, I don't, like, look at every single command on it
[47:30] because that would take me forever. But I do read, generally speaking, like, what is in there. Like, for example, we look at phase eight, right? So I get the steps. So build plus test.
[47:43] So I'm like, oh, okay, like stage one is building as both bot presents in both servers from day one. Staging is done by access control. And I'm like, oh, okay, this looks about right. And then I go like stage two is team rollout. Does this make sense, right? Because if I'm building a bot,
[47:56] when I was putting a tackle bot into Discord, I wanted to actually test that it worked first by itself before I put it into Discord where the entire team has access to it, right? So that's why I do have this like general staging that I would do. But I also ask it to give me, like, time estimates, which is kind of like it's not always very accurate.
[48:11] Because of these coding agents, you're able to do it much faster than the time estimates. So it will tell you that, oh, it's going to take, like, a week or, like, you know, 30 minutes or something. But if you use a coding agent, it takes, like, a few minutes to implement something like this.
[48:27] Is it actually true that Hermes gets better or improves the more we use it? Yes, it is true. It creates skills by itself. Yeah. your runbook is PRD plus implementation am I correct yes I think that's a good way of yeah
[48:41] yeah you know what that's a good way of putting it yes it is it's like PRD plus implementation and done so in a way that I can give to coding agents so that they're able to build the thing that I want specifically how I want it
[48:53] what model are you using for your Hermes depends on which agent I use different models for different agents. How do you optimize which model Hermes uses for each task? Okay, that's kind of like
[49:06] general understanding of different models. For example, if I want something really fast, and I don't want it to be costing me like a lot of money, and I don't want to be running a local model, for example, I would just use probably like Gemini or GPT-TERA or GPT-LUDA. That also
[49:21] means to be super fast. I would do that. I really like using cloud code, for example, in cloud but I very rarely use cloud models for my Hermes agent because even though it runs on my
[49:33] like I have a subscription I would run using my my cloud subscription I just feel like it's really expensive and it doesn't work um it's not really worth the amount of money it just it burns my credits really hard so I actually don't generally use any cloud models for Hermes
[49:48] do you have courses to learn more fundamentals on how you build I do have a lot of videos on that check them out um how do you prompt to get a good love book that
[50:02] is a very good question I kind of like I can't really show you right now because of the VPN situation but I think that that is a skill like I just like I've gotten really good at figuring out like what's the right questions to ask so I think you're just gonna have to like see it at
[50:18] of course. You just need to think about all of the edge cases as you're building the runbook and you gain that intuition over time. Sorry, I hope I can
[50:30] do a better answer than that. How to add knowledge in Hermes
[50:42] since it doesn't support RAG? By using something like an AI database, like I showed you in Obsidian. use Tina's videos for learning her videos rock oh thank you I appreciate it what model are you
[50:55] using for building the agents oh that's a good question so I'm using coding agents to build it so I primarily use codex and quad code those are my two I sometimes use open code as well but I primarily use codex and quad code quad code is what I would um use if it's something that is
[51:13] pretty like linear and just like it just needs to implement code directly right but if I want to build something that has more like images um that has needs like you know visual stuff I would use codex for that yeah okay whoa test suite all right I'm gonna continue on oops just because
[51:37] running out of time okay so yes i have some other builds which i don't really have time to show you guys right now as demos but um these are some other builds hopefully you know some ideas that you have so for example i have a coder one that is able to draft a spec i can draft a spec on
[51:53] discord and then it would go and just shift the build directly by itself so this is like autonomous coding um so i have that i also have a watchdog which is kind of boring but it's a alert channel that makes sure all my agents are online and doing okay at all times.
[52:09] I have the Wikibot, which I showed you guys already. This guy over here. Oops. Oops. I didn't know that. I have Revalbot, which I'm building as well. This is an always-on research agent that is turning things that it finds,
[52:21] like ideas that it finds online into different ideas for content, also for execution, like for building software and stuff like that. So this is Revalbot that I'm building as well. and then the newest one that I built is called Sensei um and it turns books and resources into
[52:37] skills so I don't know about you guys but if you ever like read a book especially like a non-fiction kind of like self-help kind of book it would give you like exercise it would give you like this framework you're like as you're reading and you're like wow yes amazing you know makes sense I'm gonna
[52:50] execute on this and then by the time you finish reading the book you just kind of like forget about it you're too lazy you don't actually do any of the exercises so imagine if you can turn a book into a personal coach that able to like go through everything and actually get you to execute on the books that you read so I built Sensei in order to do that so testing it out um this one I did on my bps as well
[53:14] so yeah this one is a really cool one I think if you have you want to experiment with something and you like reading books especially like non-fiction self-help books things like that this is a really cool one to build and some other ideas that I'm currently looking into as well maybe
[53:31] some ideas for you. So it would include things like productivity, like dictation to structured documents. If you're someone who likes to talk a lot into Telegram, for example, you can like dictate it or you can just directly make it into a structured doc.
[53:43] People who have like X to Notebook LM podcast. So you can pull like X with some bookmarks, like, you know, just pull them there and then compile them into a notebook. Meeting auto-transcriber, self-explanatory.
[53:58] So these are some ideas. health and wellness, like journal into Obsidian. So you can dump your day's log at night and it gets filed properly into your Obsidian. So this is another Hermes agent you can build. These are all like different types of Hermes agents, ideas that you can build with.
[54:11] On the live site, print English home control. So if you have like, what is it called, like Alexa or, you know, like any type of IoT devices that can control your home, you can also have a Hermes agent that controls that directly,
[54:26] which is pretty cool. So you get your, like, Jarvis situation. Deal Watcher, you can have an agent that is able to look at prices for you. So if you want to buy something, you want to see when it's going to go on sale, you can have a her news agent that's constantly looking at it
[54:39] and will alert you when there's a sale that's happening for the thing you want to buy. On the op side, Group Chat Digest, we have that already. So it's able to summarize a bunch of chats.
[54:52] I don't know if you have, like, a lot of WhatsApp groups or Discord groups. so it's able to summarize everything for you. Compiling skills into code. This is a really good one as well. Over time, if you build a lot of skills using LMs,
[55:04] you want to, it might be, because the LMs, if you're using text, is inherently going to be not as stable as deterministic, right? So you can also compile your skills that you're building your pipelines into code
[55:17] to make sure that it's much more stable over time. So this one is a little bit abstract, but it's a really useful one if you're someone who wants to make sure that your workflows are very, very streamlined and you don't potentially have issues that pop up.
[55:31] That's a good one to build. Yeah, so question. Which one are you excited to build with Hermes? I hope I just kind of gave you some ideas of things that you can build, like all the things that you can build using Hermes and put into the chat. I want to know, like, what kind of things do you want to build with Hermes?
[55:50] Sensei, very good ideas. I have a lot of folks. Right? Yeah. how many telegram bot I can connect to Hermes you can have as many Hermes profiles as you want and you can connect
[56:02] a telegram bot to each of them if you want yeah if we can say if we can debate a topic do you have local
[56:16] agents yes so Hermes agents are inherently all local agents and if you use a local model it's a fully local set up. So is it, it is like a Jarvis
[56:28] in real life if you train it correctly? Yes. If you build your runbook properly, you do that properly. Then yes, you can absolutely do that. How do you get the books to the box? Good question. So you can have PDFs or audio versions of it.
[56:41] That's usually the best. Honestly, because I can look at summaries that people have. A lot of people have like tech summaries as well. So you can use that to ingest into your homies to build out the skills. Do you stream on Twitch? No, I do not stream on Twitch.
[56:53] No, I did not. Maybe I should. How are your electronics learning going on? It's going good. I was showing you guys earlier, I've been building a lot of stuff with electronics.
[57:08] Kind of like building with models, but I started off just connecting with literally just sensors and different LED lights and stuff. And I'm trying to figure out how to use AR models to control them.
[57:21] so using an AI model in order uh using a model with Hermes usually with Hermes or without Hermes in order to control these like hardware stuff yeah so it's been good I would say
[57:34] I'm still too scared to actually slaughter I feel like that's the next step for me is to learn how to slaughter and just kind of scare stuff I did have to take a hardware class when I was in school but I was I think I almost failed that class I'm just yeah I don't know I
[57:49] I think at that time I was just not into hardware. Hi. Hello. Is there a better choice between Telegram and Discord? Yeah, there's a lot of choices. I just happen to use Telegram and Discord a lot.
[58:01] You can use WhatsApp. You can use, like, I think there's, like, 10, 15 different ways that you can use. I can't, like, think of them off the top of my head. Like, iMessage, like, there's a lot of ways that you can communicate with it. It doesn't need to be Telegram or Discord.
[58:15] Is it hard when you're talking about IoT? Yes. Learn to slaughter at 14 years old. Dang! That's pretty cool.
[58:29] My local AI on hermitage is so dumb. What do I do? Depends. Make it less dumb. What's wrong with this? I mean, like I said, I really think, like, learning the fundamentals, like, going through, figuring it out,
[58:42] it took me, like, a really long time to figure it out as well. Like, seriously, it really did. So if you're just, like, trying to figure it out all by yourself, constantly and assuming that your full-time job is not learning things which is my full-time job it makes sense that it's not like great in the beginning right like it's fine um
[58:58] what's the best free api provider you'd recommend i feel like if you have um kind of tense because some people sometimes they have it on
[59:13] I don't know, local models, right? Because that's completely free. If you just download them locally and use them, then they're completely free. So that's, I guess, the best API,
[59:26] the best free API is to just download the models locally. Open router, yes. Did I say open code? Yes, open router. That's what I meant. Open router, yes. Yes.
[59:38] Okay. Any other questions? Let's see. Okay, yes. So little plug again, if you are interested in building all of these things, I will teach you like all the basics as well as how like the runbook, right?
[59:53] Like how to actually go through it. I'll be actually building it on the spot. I will be doing the workshop, maybe following along. So pretty much everything I've learned over the past few months and all the experience that I have, I will be showing you all of that into like a two-hour workshop.
[01:00:06] So if you're interested, you can check it out. And I do have a guarantee as well. seven days, 100% money back guarantee, no questions asked. So I am confident that this will be really, really helpful to people who actually are interested in building the things that I
[01:00:23] just showed you guys. So that's why seven days, 100% money back guarantee. Sounds good. Any questions? oh and for anybody who wants the slides uh i do send out these slides as well so feel free to
[01:00:44] share i'll put it here you can sign up for this and then if you sign up for it i will send you the slides i just showed for this like you there if we can't be there for the live workshop can it be available for later yes it will be fully
[01:01:01] recorded you also get the runbooks um everything will be there so you can use it anytime when is bootcamp coming oh good question i can't make any promises right now we're restructuring a lot of stuff that's why
[01:01:20] i haven't done like another bootcamp because i do feel like the bootcamp i want to like make sure everything is very up to date. So yeah, not yet. What is the Hermes workshop? It is on October
[01:01:32] 3rd. Have you tried open call typically? Lots of changes since you last used it. You know what, I haven't tried it in a while. So you know, maybe I will try it. Make sure to suggest it.
[01:01:45] Yes, please decide. Okay, yeah. If you want to do the slides, then please sign up for the newsletter and we'll all send you a file in like a few hours. Yes.
[01:01:57] What is Bootcamp? Yes. Bootcamp. The AI agents Bootcamp. Yeah. We're revamping a lot of stuff. So if you sign up for the newsletter as well, we will be giving you more information about that. And if you do the workshop,
[01:02:09] you also get a hundred dollars off for the Bootcamp as well. So if you wish. Is this beginner friendly? Yes. Completely beginner friendly. No coding required. You can code if you want, but no coding required at all.
[01:02:23] I'll be showing you how to do everything, which I spent months and months doing trying to figure this out. So trust me, it's going to save you so much time.
[01:02:35] Will you be launching IoT or trusting? Would you actually want me to do that? I've been thinking, like, should I make more content? I'll be starting with content first. Should I make more content about IoT and how I'm building stuff and running models,
[01:02:47] like using devices and things? Maybe I will if you guys are interested. Can you show the coin model you said earlier was very good? Yeah, I'll do you better. I'm gonna send you a link for it.
[01:03:03] Okay. Let me find it for you. This model is the one I use locally the most.
[01:03:19] There's also a smaller version of this. The QWEN models are really good in the sense that there's so many different sizes available. So if you can't do a 36B pram, you can do the 27B pram. That's also pretty good, and they have lower ones as well.
[01:03:32] So just choose whichever. I think if you're starting off with a model, going with the QWEN family is usually a good choice just because they have so much variety that you can choose from, depending on how big your device is.
[01:03:47] That would be my suggestion. Thank you so much. Thank you so much. I really appreciate you supporting the channel. Thank you for the super chat.
[01:03:59] I can't actually see her. Thank you so much for the super chat. I appreciate it.
[01:04:15] Happy Cape Dogs. Thank you so much, babe. Appreciate it. How would you recommend attending your class if you already have a lot of things partially set up? Oh, yes.
[01:04:27] Great question. Everything that we do is going to be on different profiles. So if you do have a Hermes set up already there, don't worry at all. Like, everything we're doing is not going to affect your current Hermes. So do not worry.
[01:04:42] There's a new 27B that is faster. Yes. In the Clem family, right? Yes, I think so. I haven't tried that one out yet. How is it? if anybody has tried it. Do you think I can run locally with Lenovo Yoga ThinkPad?
[01:04:54] Honestly, I could run local models on this little guy over here. Okay, so this has, like, I think 8 megabytes of RAM. So, yeah, you can pretty much run. If you have, like, a laptop, you'll be fine of any fashion,
[01:05:08] of any source. If you have a laptop, you'll be fine. thank you rexy have you heard the new 0.3.8 i have tried it but i haven't really tested it
[01:05:25] extensively it's not i think 0.3.8 is not open it's the one that's not open source right i haven't tried it like extensively so i did try i just tried it i'm pretty sure this is
[01:05:38] Wait, is it the open source one, or is it 3.7 that's not open source? No, no, 3.8 is the one that's open source. Yes, yes, I think this one is good. This one is good. Oh, yeah, this one was really good. 3.7 is the one that wasn't open source, but I tried that one, which I wasn't sure.
[01:05:54] Can I make it on 3rd of October? Well, if you want, it is all recorded as well, and you can always email us if you have extra questions, too. That works. But up to you guys, if you wish, if you wish.
[01:06:06] um these are deep-sea models yeah one of my favorite models is the deep sea v4 pro that's probably my favorite model to use because it's cheap and it's also very multifunctional like um it can do a lot of different things
[01:06:22] bonsai is the new 27b it's smaller in size right interesting okay thank you i need to check that out. There's always so many new models coming out. 35B, A through B is so much faster than
[01:06:39] 27B on my 8GB of RAM. How are you running a 35B model on an 8GB of RAM laptop? Are you just quantizing it a lot? That shouldn't work, I think. D6 Pro is different. D6 Flash is
[01:06:55] the new one. That's, wait, I thought, no, I think those are two different families, right? Is it? Are you sure? Wait, I've been using Deep Seek Pro.
[01:07:07] Take your buck. There's so many of them. Okay, okay, good to know. I'm gonna try that out. I think I still am using Deep Seek Pro. Okay, cool. I'm gonna try it out.
[01:07:22] Why haven't we been on OpenClaw? That's a good question. So I did start off using OpenClaw, and somebody did say that, you know what, maybe OpenClaw is good to revisit again, But the reason why I switched to Hermes was because I wanted to build more capable and more extensive things that's more stable over time.
[01:07:37] And I found that Hermes was a lot more stable. And also because it's self-learning, I felt that it was just easier to use as well. That was the major reason. Although OpenCard does have more integrations, for sure.
[01:07:49] So that is true. Okay, I'm going to stay for a couple more minutes. and then I shall go to sleep because it's 11.15 p.m.
[01:08:09] Open call to this. Okay, I will try it out. But I don't know. I'm kind of liking my Hermes build right now. I think the one good thing, though, is that you can actually transfer Hermes from open call to open call to Hermes.
[01:08:23] I don't know if you guys knew that. You can actually do that. 11 15 p.m where are you based i am based in hong kong right now
[01:08:39] open call too are you still connected to notebook lm what does connected mean i use notebook lm i don't have like personal connections to google or notebook lm though do you pay for her new
[01:08:53] Asian monthly plan. Yeah, I do. I pay for Hermes, the news research, the news it's called the news subscription, news portal, news portal, yeah, news portal subscription. I do pay for it monthly. I do like
[01:09:05] the $20 one. And I kind of like top it up if I'm doing something that is a little bit more expensive. Okay, oops, I disappeared.
[01:09:18] Okay. Cool. Alright, thank you guys so much for joining. I hope this was helpful to you guys. I really hope this was helpful.
[01:09:30] This was a lot of fun. I haven't done a live stream in a while. Okay, cool. Thanks, Richard. Deep six. Good. Pro is still there. Good to know. Great. Yes, I hope this was helpful for you guys.
[01:09:43] I hope you can see, like, how much stuff that you can build with Hermes. I've had so much fun building with Hermes in the past, like, few months. So I really hope that you guys are able to have fun doing it as well. And for those of you who are attending the workshop, thank you so much for choosing to attend this workshop.
[01:10:00] I promise that we will try our absolute best to give you the best value possible. And everything that we have learned, experimented, done for all these months of pretty much grinding it out every single day,
[01:10:12] we're going to come past that all together so you're able to build these things I'm showing you right now. Build anything, really. After you learn how Hermes works and the mechanism for building, how to come up with a runbook, how to use coding agents, literally, you'll be so shocked by how many amazing things that you can build using Hermes.
[01:10:30] So, really excited to be able to unlock that for you guys. Thank you so much, and I will see you guys in the next video or live stream. Have a good rest of your day. See you!
[01:10:48] Thank you.