The Startup Ideas Podcast - Hermes Agent clearly explained (and how to use it)

Starting point is 00:00:00 Hermes agent. You're seeing it everywhere. People are calling it the open cloud killer. And today's episode is about how you can actually install it, how you can connect it with G-Stack by Gary Tan, how you can connect it to Obsidian, how you can create skills. We go through step by step, how you can get started with Hermes agent. This is everything you need to know for how to run it, get started, and actually how you can even use it on an Android device. So enjoy the episode. It's with my dear friend, And Imran, who just explains technical concepts in such as a clear way. It's a breath of fresh air. Enjoy the episode, the introduction to Irmez agents.

Starting point is 00:00:38 I begged them to come on, and Imran has come on. Thank you for coming on. By the end of this episode, Imran, what are people going to get? By the end of this episode, you'll learn how to install Urmez agent, which is the best personal agent. It has built-in memory. It learns about your workflows and helps save you time, money, and allows you to do more. and I'll even show you how to install it on an Android phone. Okay, cool. Yeah, so I've been hearing a lot about Hermes.

Starting point is 00:01:13 Obviously, it's going viral. Is it the new OpenClaught? I don't know. Imran, I just need you to explain it in the simplest terms, the most clear terms, so that at the end of this episode, I can actually go on my computer, get Hermes going. So you're committing to making it as clear as possible and sharing as much sauce as possible? Exactly, yeah, that's what I'll do. All right, let's do it. All right.

Starting point is 00:01:38 So the first thing, the way that I found Irma's agent was that I tried using open claw. And when I was using open claw, I ran into basically three massive issues. The first issue is that I kept having to tell it to do the same things over and over again because there was no built-in memory system, right? And this is a common problem. The second problem I found was that I had to keep restarting the gateway. I think there was a day where I had to restart the gateway once an hour. And so that was really useless.

Starting point is 00:02:06 I felt like I spent more time setting up OpenClaude than I was actually like using it to make my life better. And the third big problem with OpenClaught for me was just that it was eating up tokens. And I had no visibility into how or why. So I quickly migrated over to Nebula, which is if you're looking to build, if you're looking to kind of have just like an AI coworker, Nebula is probably the better tool. But if you want to have like personalized workflows, if you want to kind of tinker under their hood, and you want to have a system that learns over time, I highly suggest using Hermes.

Starting point is 00:02:38 So the three things that Ermes does better than OpenCla are basically solving the three problems that I mentioned. One is that it has a built-in memory system. So every time you complete a task and successfully complete it, it automatically writes to its own memory. This way, like over time, it gets better. It also uses a typical like normal SQLite database, which is the same type of database

Starting point is 00:03:02 as normal web applications. And what that allows it to do is search in real time for times where it's done something successfully for you. So if it didn't save it to its memory, it can actually go and search through all of the logs of all the things you've asked it to do and remember it. Even things like API keys, if you forget to save them to an environment variable,

Starting point is 00:03:23 but you kind of passed it to the agent, it can actually search through and find it for you. And the last thing is, it's just more stable. Like I haven't had to restart it in like over a week, which is way better than what happened. with OpenClaugh. So I'll walk you guys through the installation, but before I do, Greg, do you have any questions so far? Yeah, I mean, I guess I'll see by the end of this, but, you know, for me, it's like, I think a lot of us listening, like, we might have heard of OpenClawe or might have

Starting point is 00:03:50 installed OpenClawe. You know, I'm just, what I'm begging to know is like, what I don't want, actually, I should restart. What I don't want to have happen is I install Hermes and then a week later, I go back to OpenClawe, basically. You know what I mean? I just kind of want to pick an ecosystem and be like, this is my personal agent. No, it makes a lot of sense. And that's kind of the problem that I was having before.

Starting point is 00:04:17 I kept switching and jumping between different agents until I landed on Hermes and I've been using it for over three weeks now, which in this space is a lot of time. So before we get into the installation, I'll walk you really quickly on my setup. So when you just type in Hermes in your terminal after it's installed, it's going to to open up my Xcode MCP, which is not running right now, so it'll fire up in a second. Cool. Yeah, and I'll zoom out a little bit.

Starting point is 00:04:44 You can see here when you open up Hermes for the first time. On the top, you'll see the available tools. So Hermes comes built in with 40 plus built in tools that OpenClaude doesn't have. So you don't have to go find out which tools to install. Many of the built-in tools will cover almost all of the basic tasks that you'll need to do. If you want to fire up a browser, if you want to search the web,

Starting point is 00:05:07 if you want to create recurring scheduled cron jobs or like scheduled like code, it has all of that built in. Even things like image generation are built in, home assistant capabilities. You don't really have to configure or go figure out what the best tools are. The other thing you'll notice about Hermes when you first install it is that it has a lot of the really most popular

Starting point is 00:05:30 available skills pre-installed as well. So like I'm on a MacBook, so it has all of like the Apple notes, Apple reminders. It's got Find My, it's got IMessage. I did not have to go and find this from a skills hub. It was already ready to go as soon as I installed it. So if you want to talk about simplicity of installation and having all the skills you need, Hermes is probably the best one for that. What about security? Like are those, like if I install some of those skills, are those, like do I have peace of mind knowing that that's secure? Yeah, no, that's a really good Good question. So there's a couple ways around this. One, I think you can always ask the agent to do an audit of your security setup, which a lot of people don't think about. It's kind of almost like metaprompting it. So Hermes has knowledge of where the keys are stored in your configuration. And you can say, like, is this a security setup? Tell me why or why not. And it'll go through and let you know if there are any secret keys exposed on your computer. If they're in plain text, if like a firewall is set up poorly, it'll let you know. The other thing,

Starting point is 00:06:34 that's very unique to Hermes is that it's built to also out of the box be able to be ran inside of a Docker container in case you want it on your machine, but isolated from the rest of your files. And then you can also run it on modal as like a serverless service as well. So it's really flexible in how you met. I personally am a little bit risky and I just kind of run it on the bare metal. And I'm just routinely making sure like every day I'm updating it. And I'm also making sure that like I ask it to, you. you know, secure my own setup. Cool. Let's keep going. All right. So the installation, if you're on a Mac, is pretty straightforward. You can just head over to the Irma's agent documentation. It's on the new research website.

Starting point is 00:07:19 And if you're on Linux, MacOS, or even Windows subsystem for Linux, it's just this one-line command. If it's your first time installing a tool like this on a Mac, you'll probably need to install the Exco developer tools. So I cover that in the video that, Greg found me through, but basically you would do like Xcode dash select dash install. You can see this command right here and I will actually run it here. I already have it installed. You can see.

Starting point is 00:07:47 And if you need to update it, you can update it later. So yeah, you can just go ahead and copy this command and paste it in and it'll run. Now, obviously, I haven't installed this already. So it'll just go through the update. Another thing that I found was that you can actually skip the, you can skip the onboarding and you can just close out of it. And the most important commands that you'll need to know once you have it installed is just this one right here, which is Irma's model. So this kind of brings me into the next problem that I had with OpenClawe, which was at with OpenClaught,

Starting point is 00:08:22 I just did not have enough visibility into how much I was spending on tokens. And it was like a constant battle to figure out like exactly which model to use. Oh, wait, I got to run the install again. Let's try one more time. I think I broke it. Also, with OpenClaw, you can't use Anthropic anymore, right? So with Hermes, can you use an Anthropic API key seamlessly? Correct.

Starting point is 00:08:51 Yeah, you can use an Anthropic API key. You also have access to the new router as well. So let me show you. Right. So this is one that's running on my gaming PC. I have this as a backup. So if we type or let me clear this. So it's easier.

Starting point is 00:09:07 Now type Firmaz model. And here you can see these are all the different providers that you can use to select a model. Again, this is all out of the box. This is all like out of the box. I did not have to go install anything. And the two biggest ways to save money on this is really just to use either the new portal or open router.

Starting point is 00:09:28 So if I go on open router, you can see I'll be able to see all of the different models. And the cool thing about open router is that that every once in a while, you'll have some free models available. So here, Nvidia's Nemotron is free this week. So if you wanted to use that model, and you just want to run for completely free,

Starting point is 00:09:47 it's available as well. You can see also through OpenRouter, I'm able to access Anthropics models here. Remember you're asking? So they're both available. And you can see a very clear layout of exactly how much it'll cost. So if I want to use Quinn 3.6 plus, it's probably only going to cost me 30.

Starting point is 00:10:05 to three cents per million tokens for input and about $1.95 per million tokens of output. And you can see the price difference between Sonnet and Quinn, right? So it's almost like one-tenth the price on the input tokens, which is like really good. And you sort of know in sense, like you know how much you're going to spend on tokens. You don't really know once you have it set up, like how much, you know, what your date. Well, I mean, you'll find out basically. Yeah. based on the task you give it how much things are going to cost.

Starting point is 00:10:40 And I think that that's sort of the issue I think some people are having is like they're spending. I mean, it's not crazy to spend hundreds of dollars a day on your open claw instance at this point. Yeah. So actually one of the interesting ways to fix that using the Irmez agent is that you can actually, once you have a task that you know that you want to run, like on a run. recurring basis, you can actually have it write the code one time for it. So instead of requiring an agent in the loop every single time that you need to do something, you can actually write the code to make it like more deterministic. And that'll actually long term save you tokens because you won't be spending tokens on actually

Starting point is 00:11:22 like doing the processing every single time. Like instead, you'll just do it the first time, get it to write the code. And then, you know, if you're using a free model, you can use the free model to write the code. and then you basically will spend no tokens on that singular skill or task forever. That's like another thing that I noticed. I realize that a lot of people are not, if you come from a software engineering world, you're always kind of thinking in this methodology of like,

Starting point is 00:11:46 don't repeat yourself. So like if you are like in the habit of like building reports every single day or you want like a kind of like a daily digest, a lot of those things can be automated with just pure code instead of relying on an LLM to do like a web scrape or something like that. And that will also save you a bunch of tokens. So by just switching to Hermes agent and OpenRouter, I basically got my token spent down from like, it was like about like $130 every five days down to like maybe like $10.10 every five days. So about like a little bit over a 90% reduction.

Starting point is 00:12:18 And I'm still able to do all the things that I want to do. The other important thing that I think everyone will want to know is that of course, Hermes agent does allow you to have a connection to Telegram. So you can see all my agents here are named after the Muppets. So I still have a lot of room for expansion. If I need to add more agents, there's still a bunch more Muppets I can go through. And I can talk to them in Telegram, just like how I can talk to them inside of the terminal. And this Cookie Monster one is super special because if you kind of take a sneak peek at the screen here, this one is actually running on a Sawana Seeker Android phone that I have right here.

Starting point is 00:12:57 So I wanted to talk a little bit about that because I got this setup finally yesterday. If you want to set up Urmez agent on an Android phone, you'll see here that there's actually the same way that you install it on your computer, there is a script that you can install to put it on an Android phone. And so here I have installed it on the Android phone and you can see what device am I on? And it says here, I'm on a Seeker, Android 15 phone running via Termox. That's really. Yeah.

Starting point is 00:13:27 And then people are like, if some of the people who saw that I was doing this on Twitter, we're asking like, oh, like, why would I install it on an Android phone instead of installing it on a computer? So before I get into that, I will say that there are a few extra steps for installing it on Android. The first thing is that you need an app called Termux. Termux is basically like a terminal inside of Android. So it'll kind of look exactly like your normal Mac terminal. And then if you want to extend it even further, there's another app called the Termux API. And the Termox API app, it's available on the FDroid, which is an open source Android app store.

Starting point is 00:14:07 But the Termox API actually gives you access to the sensor data on your phone. So you can access information about the battery. You can change the Wi-Fi network. You can change the volume of the device. You can take photos using the Android phone. You can adjust the brightness. You can trigger the vibration motor. There's like all basically everything that they,

Starting point is 00:14:28 the Android phone has access to, you now have access to. So you can imagine a world where, instead of having this running on a Mac mini, which is sold out, you can have it running on an Android phone that's, you know, Android phones are very cheap. And you can put a SIM card inside of it. You can bring it with you. You can have it read your text messages that are sent directly to that number. You can automate basically like two-factor authentication that comes in via SMS.

Starting point is 00:14:53 And basically like you now have a version of like an always on low. power dedicated agent device that isn't a Mac Mini and that isn't as expensive. A lot of people listen to this podcast, the startup ideas podcast, because, you know, I don't just bring on people who, you know, give practical AI tutorials, but also they like ideas. They like ways to make money using some of these, you know, new technologies and stuff like that. You know, with the Android-Urmez instance specifically, like, do you have any ideas that come to mine around like, okay, you know, if I were trying to make money with Hermes agent on Android, you know, what are some things that come to mind, top of mine?

Starting point is 00:15:40 Yeah. The first thing is probably because you have access to the Termux API, you can actually fire off commands on the Android phone itself. Like you can tap the screen and you can like send notifications. So if I think one of the next things I want to set up is of course, like everyone, some sort of like social media automation that uses the phone directly. So right now we have a lot of scheduler tools and people complain that social media scheduling tools, they nerf your reach because, you know, like they're going through the API instead of on the device. Well, this kind of solves that because you can actually post the content directly from

Starting point is 00:16:15 the device. That's one thing that's like super cool, right? So instead of having to, you know, literally like open up your phone and download a video that's generated and post it that way, you could have this technically run. running on an almost infinitely scalable amount of Android phones and run accounts and post from there. And it will still show that it came from a device with like a real Mac address. That's one way. Another thing that I've seen is just, of course, like there's like the make money part of it.

Starting point is 00:16:43 But also, you know, I have a lot of the very basic parts of my life that are annoying, like already automated. So like I have an email triaging agent that every morning goes through my emails, deletes the ones that are unnecessary, unsubscribes from things that I subscribe to that are really useless and then shows me a digest of the important emails. That might not directly make me more money right now, but it's still saving me about 30 minutes to an hour a day and just allowing you to do more. Cool. Yeah. I think the hard part is just figuring out, like taking stock auditing your personal life to be like, what are the things I need automated? And then also from a business perspective, what are the things I need to be automated? I think that's part of the hard part.

Starting point is 00:17:25 And I guess like, you know, you could, you can ask Hermes agent to audit your life, right? And start asking you questions to help you. Like, ask it to help you, you know? Yeah. Like, we can do this. Like, where do I spend the bulk of my time? And let's see if it knows from my memories. And if this gets too intimate, we can always cut it out. That's what we want, Aaron. We wanted to get into it. Yeah. So like it knows where I live, knows what times that I'm in. It's like, okay, where do I spend time?

Starting point is 00:17:55 What am I asking questions about? That's awesome. Is that something that you recommend people, you know, use Airmez agent to help help you set it up and productize some of the stuff that you're doing? Yeah. So I think like the idea of using agents to get things done is like a new paradigm. So the easiest way to like get used to it is to solve like personal problems in your life. So the biggest like personal problem that I first solved within age.

Starting point is 00:18:21 agent was like figuring out what to cook at home because my wife and I like we love door dashing we love eating out but obviously like that's not you know that's not the healthiest and that also costs a lot of money so the first thing I did was I set up a local speech to text model on my actual computer and I sent a long like eight minute telegram voice message of me going through my fridge and my pantry of every single thing and every single ingredient that's in my pantry and I said every day can you send me a recipe or three recipes based on what's in my pantry and what my fitness goals are. It seems like something small, but it kind of takes a lot of like mental load away from like my day to day. There's a lot of things like I think that if you start

Starting point is 00:19:03 doing like really basic stuff like that, you know, like we can, you can kind of automate a lot. Also, we got to cut this out, bro. There's a lot of personal stuff in here. There's no way. There's no way too much. Rafael, let's blur it out. We're going to blur it out so people can't see it. Okay, we have to blur this out. It's a lot, bro. We're blurring it up, but we're keeping this in the sense that like, if you do this, it works. Exactly. Yeah, it does work. It's very intimate, so definitely can't show you guys everything. Well, it's intimate also because it knows you, right? And you've put in the work with it, right? So if you're starting this from scratch, it won't be intimate, right? It won't be. Yeah. So like, when you start it

Starting point is 00:19:43 from scratch, like, you'll have all the tools, you'll have the skills. As you talk to it every single day and you use it for work over and over again, it'll, like I said, it'll store in its memory. It'll begin to learn exactly what you do and how it can help you. And you can even ask it. Like every night, you can ask it. Like, what's one or two things that you can build for me? That would make my life better. And it'll do that for you. Okay. What are other must-know things about Hermes agent? You do still have to update it every night. It's still technically beta software. So you can see, I haven't updated this one since in nine. days and I am 535 commits behind, which is quite a bit.

Starting point is 00:20:24 So you do still have to update it every single day. It is still technically beta software. You still should probably constantly, you know, lock it down in certain ways. A really simple way to lock down Irma's agent, but still have access to it from anywhere, is one to set up like Telegram or WhatsApp. Another thing that I highly recommend for any of these tools is that,

Starting point is 00:20:47 you install tailscale and you configure tail scale correctly. So tail scale will allow your phone and all of your computers to be on the same kind of virtual network. And then you can remotely access them using any like terminal SSH app, which just lets you kind of remote in and like monitor it and chat with it that way as well. Before we head out, is there a question that I should have asked you about Hermes agent that I didn't ask you? Should you migrate from OpenClaught?

Starting point is 00:21:15 I mean, I've got my, yeah, I mean, that's the big question, right? Should you, now that we've seen it, I mean, well, we've sort of, you know, I should have, let's actually, would you be open to showing your Muppets? Yeah, let's show my office, yeah. And also, like, with respect to your Muppets, like, does it make sense to set up, you know, one agent, multiple agents? Like, how do people think about designing their, their agents? Do I create one that's called social media manager? And it's just doing social media stuff.

Starting point is 00:21:54 Or how should I think about this? Yeah. So this is something that's still kind of a work in progress for me as well. So you can see count is my main kind of agent. This is the one that's running on my gaming computer. And you can see this has all of like my personal stuff set up. So I have cron jobs for like doing my Gmail triage for unsubscribing to emails to give me like expense reports, like some more personal stuff, like finance stuff is all set up here. These are technically

Starting point is 00:22:21 cron jobs. They're not subagents. I have seen people set these up as subagents. The benefit of that is that you can assign specific models to each one. So I could have a Gmail email triage subagent that I have assigned a cheaper model to, right, because it's more deterministic and it'll tell me, like, if it's like a really simple task, you can assign a cheaper model to it and kind of save money that way and you can add more specific instructions. But I've also seen people just set it up as a cron job. So I have it set up as a cron job. I don't have it set up as a sub-agent.

Starting point is 00:22:54 So I think a lot of these kind of specifics are still being figured out. We don't really know if it's better to have it as a sub-agent or not. The thing that is that we can agree on is that having an agent that has memory and learns over time is incredibly powerful. And I have four set up here just because I'm like a tinkerer, but I actually think the most optimal way to do it is to have one setup or two. And the only reason why I say two is if you have one for work and one for personal stuff, like I imagine if I worked at like a Fortune 500 company,

Starting point is 00:23:30 they wouldn't let me like run Hermes agent with all my personal stuff on it on my work computer. But I still want to have the capabilities of being able to kind of like automate or do work really efficiently. it's also it feels cleaner a little bit if it's personal and work like my to do list for example I have like the way I run my life you know I use things the to do to do app and I just have personal and work and like to me that just like makes the most sense so like when I the way I'm going to set this up after this call is I'm going to set up a personal one I'm going to set up a work one Yeah, and I think another thing that maybe we didn't cover that I think we talked about a little bit on Twitter is that this is like Obsidian. So I was never a big Obsidian fan.

Starting point is 00:24:15 I kind of just stored everything in my Apple notes and kind of hope for the best. The cool thing about Obsidian is that even if you have like multiple agents, it's all like markdown files. So now this tool that was like instead of having to know markdown, you can just tell agents to like organize them. So I have this kind of setup as just like my home MD file. So it tells me all the important things I need to know about this week. It tells me about things I need to get done today. Upcoming travel, things for like my day job, things for like, you know, personal stuff. And it's all organized and set up automatically by the agent every day.

Starting point is 00:24:50 And so I would not have been able to go through like the painstaking effort of like putting this together by myself every single morning. But now like I have an agent that does it for me. And it's just so much easier. But this is not something I would have done before. I wouldn't think to use Obsidian in the past, but because I now have agents that can kind of manipulate it really easily, it just makes it much more fun and easy to use. Right.

Starting point is 00:25:15 So is your recommendation that once you get Hermes installed, post-install, start using it with Obsidian? I think Obsidian is a really clean layout. Because if you look at, like, if you look at Telegram, like some of these just kind of read as like massive, walls of text and even if I organize it or even if I put something in my sole MD file to specify that it should

Starting point is 00:25:41 speak concisely like it just becomes really unruly and it's like really hard to find like the most important information. There are people that are like experimenting with building like kind of like mission control dashboards. But I just feel like the easiest is like the one that you can see on your phone and your computer, you know. And if someone saw your obsidian and it's like man, Amaran has really, like that's my dream.

Starting point is 00:26:06 How do they go from, like, how do they make a similar thing? Like, how do you actually do that? Yeah. So my obsidian was set up by my Hermes agent after using my Hermes agents for like 20 days. So as it learned about me. You think it takes 20 days? No, I think it takes building up the habit of using, of default going to the agent to get work done, even if you can do it yourself. That's the biggest thing.

Starting point is 00:26:32 Okay. So maybe it's like seven days. Maybe it's seven days of like using it, you know, consistently. And then after that, the Hermes agent knows a good chunk about you. And then you can have it create a similar obsidian stack. Right. Yeah. And you still, right now, you still kind of have to metaprompt it.

Starting point is 00:26:55 So you can ask it at the end of every day. Like, what is something you should build for the work I do? Or what is one way that you can. what is like one one task I'm doing over and over again that I should set up as a cron job and it'll know but you still kind of have to prompt it right so I'm hoping in the future that you don't have to do that that it just kind of knows automatically but we'll get there we're pretty close that's really interesting could you like open up I know this is we're starting this live but like could you open up like a dock just so and and just like write out like the

Starting point is 00:27:27 the prompts that people should should be thinking about around around for a mez agent like what are the ones that you're using emron that you're like it seems obvious to you but you know people might you know not know yeah a really basic one is like what have i been procrastinating right that's a good one because you has access to your to do list if you're listening to this podcast like you're probably doing a lot and there's probably something that's like, you know, under the hood that like you just haven't gotten to yet. Another one is what is the most important thing to work on today? Right.

Starting point is 00:28:06 And like that's like super important. Another one would be like I mentioned, like what are some tasks that I'm doing every single day that I could or should automate? Another one would be what is a tool that you can build me tonight that would make my life easier tomorrow? tomorrow. Right? Like these types of things like where you're yeah, you're right. This does kind of seem obvious to me. But to many people, like it's kind of a new new way of thinking.

Starting point is 00:28:39 I'm trying to think of another one. Is there anything important today that I missed, right? Anything around Cron jobs, MD files? I'm trying to think. Yeah, I think, I think, I think, I think, the cron job setup could be is like a little bit difficult in the beginning because I feel that people don't understand like what a cron job is. It's still a very technical term, but it's essentially just something that runs on a schedule. And you like everyone does, everyone has a list of tasks or a list

Starting point is 00:29:16 of things that they do every single day that probably could or should be automated, right? And so asking it to set up cron jobs for those things will just kind of make your life a little bit easier. The last thing I did want to show you now that I'm thinking about it is I actually have, I want to show you there was a psychiatrist that made a computer, or made like a computer program. Yes, his name is Joseph Weisenbaum. And he made a natural language processing computer program over the course of three years at MIT that's basically like a chatbot therapist. And I've actually loaded this up as a skill inside of Hermes where I can talk to it every single day and like help it. It will basically help me self-actualize about what I should also work on. So there's a lot of these like weird like little like niche like personal development things that you can actually build really easily.

Starting point is 00:30:18 It took them three years to build out this natural language processing, like kind of like psychiatrist thing. But like you can just drop this Wikipedia file inside of your Hermes agent and say like you'll turn this into a skill and it'll do it. That's really cool. Yeah. Yeah. That's sort of the daunting part about, you know, be it open claw or Hermes is like you

Starting point is 00:30:45 sort of need the ideas around like I'm sure a lot of people wouldn't have come across that, you know, Wikipedia article and been like, oh, I should. make this a skill, right? So the prompting yourself to actually think about like, oh, I'm navigating the internet or I'm navigating the world. How can I make this a skill so that I can use this every day? It just has to be a part of your, it's just how you work today in the AJI. Yeah, exactly. The biggest thing is learning how to use Irma's agent is not actually the skill. It's going to become the requirement, you know. Exactly. Yeah. And whether it's like Irma's today, maybe open cloud gets better, maybe Claude

Starting point is 00:31:23 co-work, maybe it's nebula, whatever it is. Like, you still need to know what to do with it. And that's, like, kind of where it counts. Last question around skills. I know that you showed some pre-built Hermes skills. You know, what are some, you know, must install skills that you recommend for people listening? Yeah, so I definitely recommend installing the obsidian skill. I actually don't even use the obsidian CLI,

Starting point is 00:31:54 but I use the obsidian skill. That one's really important. I've seen some people install the honcho dev memory skill. I haven't needed to set that up yet, though I think I probably will, because there are some memory limits on Hermes, and you kind of want to keep your context as small as possible. Another really useful one,

Starting point is 00:32:15 let me see from my ghosty. Well, so a lot of these skills I've built myself, right. I have like a bank statement analysis one. So I definitely think like whatever you do, you should always like start with like try to build out your own skills around like personal finance and like fitness and like all the things that you already pay for. And maybe those aren't ones that you actually go down on, but they're ones that you build. Another really interesting one that I think everyone should play around with are of course all of the software development related skills. I even, you can see here I actually ported over G-stack by Gary Tan

Starting point is 00:32:51 into Hermes before it was widely available on Hermes. So I definitely, you know, if you're working on a startup, it's definitely like a really cool skill to use G-Stack. And yeah, like I think those are the big ones. Just because I think some people don't know what G-Stack is, can you just give a quick primer on what G-Stack is and, you know, how, why you think that people should install G-Stack with Hermes? Yeah, yeah.

Starting point is 00:33:17 So G-stack is basically the way I understand it, is it was, it was, built for Claude Code, and it was made by Gary Tan, the CEO of Y Combinator. Essentially, the idea is that it takes the Y Combinator style startup process, which is like figuring out what works week over week, asking the right questions about what you should improve about your product and your business, and then helping you go and implement that as code and make decisions on that. So those types of things were previously only available to people who were in Y Combinator, which was like the best, which is like one of the best startup accelerators in the world. But now a lot of that knowledge has been basically open sourced as a skill that you can bolt on to your agent.

Starting point is 00:33:57 And that's something that was never available before in the past. So if you're obviously working on a startup like an app or something and you're not in San Francisco or maybe like you're not familiar with like the startup methodologies, I highly recommend using something like that. And it's a no brainer. It's free. It's free. Yeah. Yeah. It's like the agent itself is like it's like Irme's agent is like basically like it's like it's like.

Starting point is 00:34:21 90s tuner car culture, right? Like you can go find the parts you want and you can put them on and you should like learn how to customize it for yourself. As long as you remember that like customizing it is not the skill, but it's more about what you get done with it. Right. I think it's like you do have to remind yourself that, I like how you said, that customizing is not the scale and there's so many people who are just obsessed with the customization and

Starting point is 00:34:46 then they're not actually doing anything, right? So it's like don't be an artist about it, right? Like at the end of the day, you want something that's going to add value to your own personal life that's going to add value to your business life. And it's a rabbit hole basically to go down in where you're like optimizing and optimizing and optimizing. But don't do it. Yeah, this handles the optimization for you. Like the biggest thing when people say, like, a lot of people have asked me, like,

Starting point is 00:35:22 what's been the most useful thing about like Hermes agent? Like day to day, I work out of fund and I'm able to talk to more founders and have better conversations with them because a lot of the background work is now handled by my personal agent. That's awesome. That's a huge win for me. If we can talk to 20% more companies or 30% more companies, we have better signal, we get better deal flow.

Starting point is 00:35:43 We're helping out more founders. We're eventually going to return more as a fund, right? It just makes me better at my job. It's a big deal, right? Yeah. That's the way I see it is like if you value your time at, say, $500 an hour in terms of the opportunities that could come, that's a huge deal. So, Imran, thank you so much for giving us, you know, the go-to guide for installing Hermes agent, playing with Hermes agent, making skills, installing it with G-Stack and obsidian. I really appreciate it.

Starting point is 00:36:15 I'll include links for where you can follow. on the internet, which is where I found him. And I think that you're super talented at explaining technical concepts in a really simple way. So I would love to have you back on the show. But people, let me know. Let me know in the comments. You know, is this, did you feel it? I think he brought this off.

Starting point is 00:36:39 Thanks again, Imran. Is there anything you want to leave people with? Yeah. I work at a fund. It's called Alif. Check us out. alif. build a l-i-f-f-b-u-i-l-d and of course i'm on social media at imranier i think after this i'm just going to make more videos so let's do it yeah let's do it all right thanks a lot

Starting point is 00:36:58 all right thanks for having man

The Startup Ideas Podcast - Hermes Agent clearly explained (and how to use it)

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.