Hermes Agent OS Just CHANGED Everything 🤯

Hermes agent OS just dropped. So this is the most powerful thing you can do with Hermes right now. Right now, most people are running their AI agents all over the place. Hermes over here, Claude over there, OpenClaude somewhere else.

None of them talking to each other. None of them sharing memory. None of them working as a team. That ends today, my friends, because I'm going to show you how to build one mission control dashboard that runs all of your AI agents all from one place at the same time, 24 seven.

That means one screen, every agent all connected together. And when you set this up, your whole AI system gets a hundred times more powerful overnight. We're talking a full content studio, a full SEO system, a Kanban board, a memory system that never forgets a single thing you've ever worked on, all in one place. And you can use it for free.

There's actually one thing I'm going to show you later today that most people completely skip when it comes to this. And it's a thing that makes this whole system actually work. Stick with me to the end and I'll show you exactly what it is. Let's get into it.

Today, I'm going to be showing you a whole powerful system with Hermes AgentOS, right? So this is basically agent operating system for Hermes. And what this allows you to do is build out a system, and I would recommend this for anyone watching, no matter what you use, whether you use Claude or whatever, build out a system where you can manage all of your agents and operate them from one single system in one single place, right? And I'm going to show you some examples of what we've built recently.

So if we go over to the workspace here, you can see that we can preview all the apps that we've created, right? This is all stuff that we've literally generated with Hermes Agent, right? Now, on top of that, we actually have videos over here now that we can play back and everything that we've created with AI agents, we can print out here. As you can see, we've got images, we've got, for example, text to speech and podcasts that we've generated.

We can even operate this from Notebook LEM. And the whole point of this is that if you're using AI in any single way, I would recommend that you put them into a system. And this is what we're doing here. And it makes Hermes, it makes all your other AI agents 100 times more powerful, right?

You can see here, we've got skills that we can manage. We can manage your status, we can manage all the sessions without privacy. We can manage our camera board. If I want Hermes to build out a full website like you can see right here, it can just go off and do it, right?

It can go off and create whatever I want. And it's pretty amazing. So for example, I can drop a to-do list here. We've got 12 different agents ready to go with Hermes, different profiles with Hermes.

And then if I'm like, okay, build out a full content strategy from SEO and the website itself, you can see here, the tasks are just ticked off. It's in my Kanban, I can come back to it later. We've got a full 12 month content calendar over here. And it's just amazing.

So to recap here, you can have swarms, big autonomous teams of AI agents who work and go off and do other stuff. You can have a memory system where everything is connected, all the context, everything in your life is just connected here so that you've got everything working together, which is pretty amazing as well, right? You can see how it works right here. This is our knowledge base.

And the AI agent basically has notes and memories on everything that I do and everything that I work on, all the tools that I use, all the memories, everything else, right? And then we have notebook land where we can generate videos, we can generate podcasts. We've got a studio where we can generate videos and text to speech and images as well. We have an SEO tool where we can deploy to websites and create content and rank it about whatever keywords you want to do across five different websites at the same time.

And so my point here is you can build this out. Now, if you're wondering, okay, how do I do this? How do I do it? Basically what you wanna do is whatever idea you have in your mind about what you think you need or what you work on day to day, build that out with this, right?

Tell Hermes, okay, go off, build out an agent operating system and allow me to host it locally, right? That's what you wanna do. And then it can go off and do it for you. So you can go inside the chat here and you say, build out a mission control.

Here's how I envision it looking. It's not gonna be perfect first time round, but if you work on it every single day and you tweak it exactly how you want it, it's only gonna get more powerful. It's only gonna become better and better. Now, I do have my full system inside the AI Profitable, and if you just wanna get the zip files and the prompts from me directly, but if you want to set this up yourself, that's how I would approach it, right?

Like I mentioned, just ask Hermes to build out. The other thing that I would say here is it's just much easier than the terminal, right? So if you go over to the terminal with Hermes, I don't really use terminal with Hermes anymore because it's super confusing to use. You don't really have any history of what you've worked on.

It's quite hard to see multiple profiles. Obviously inside here as well, we can only manage one profile. And then most people are not gonna use the terminal, right? It feels like a little bit like the 1990s if you're using a terminal, right?

Unless you're really technical and you're great with terminals, which 99.9% of people watching this are not, then I would recommend we use a beautiful interface like this, right? It actually feels good when you use it as well. And the other cool thing about this was you can say to Hermes, okay, build out this dashboard, here's how I want it to look, but also add in OpenCLR, add in Cloud, add in Gemini, add in Antigravity, add in Codex, right? And then that's basically what we've done.

We've got all of our agents sitting there working off the same memory system and helping us rank with SEO, helping us create whatever we want. I can even set like daily goals inside this section. I can journal over here. I can flick between my previous journal entries and that's pretty cool as well.

And then we have this mission control dashboard where we can just see everything in one place. So we can see the status of Cloud and OpenCLR and Hermes. We can see what versions our agents are on and what models they're using and everything else, right? And the other cool thing about this as well is like you can use something like our alpha, which is a free API, and then you can use that to power Hermes itself.

Now I've had loads of questions about this. If you're watching live, feel free to drop any questions as I'm going along. I've had loads of questions about this inside the Air Proffer Boarding. So I want to just answer it today and walk you through it.

The other thing that I would say here is like every new skill that you add on to Hermes can be used inside this system here. So if you've, for example, taught Hermes computer use and how to use your computer, which is a skill that I've put in here, then I can just use it from the agent workspace right here. And it's much easier to manage, much easier to use and much better to use that way, actually. So that's the way that I look at it.

So let's have a look at some of these questions that we've had recently, and we can run through exactly how to handle everything. Now we'll say, for example, Dr. John Meza, he builds out his own agent operating system, as you can see right here, pretty cool. And he used our system, right?

And he said basically it wouldn't be possible without this. So it's pretty cool. What else you got here? Maha says, is agent operating system open source?

So I just give it to members inside the AI Profitable Room, right? That's how you can get access to it. So if you go inside, if you're a member already, just go inside the classroom here, then go to the new daily updates, go to the agent operating system section, and you'll see a video tutorial on how to set up. You'll see when it was last updated, so you know you've got the latest version.

And then also you can see the zip file down here. So if you wanna get my version, again, you can build it yourself, but if you wanna get my version, it's all inside the AI Profitable Room. Link in the comments description or go to the AIprofitableroom.com. So let's talk about this.

We've got a bunch of questions here that I'm pretty excited to answer. So the first one was from Rachad. And by the way, if you, like I said, if you have questions, just like I answered Maha, ask your questions as you're watching this. So we've got seven questions from the AI Profitable Room.

This is something that I do, I just answer people's questions every day and then give them a video tutorial breakdown here. So Rachad was asking like, hey guys, I love the agent operating system that was built. For example, one for OpenCloud, one for Cloud, one for Hermes. And Rachad said, I own and operate e-commerce stores.

So I wanna automate a few things, like for example, research, image generation, video generation, et cetera. How do I do it? Or what's the best way to do it? So here's the way that I would do it, right?

So if I'm, for example, trying to do research, I would actually plug that into Hermes directly. And if you're, probably the best API, just from everything that you're doing here, the best API that you can use, because you can use three different methods here, is you can use Grok 4.3, right? Now Grok 4.3, which I've got plugged into Hermes right now, you can log into that with OAuth, using your Twitter account. If you're already subscribed to Twitter, you don't even need to subscribe to anything else.

You can plug that into Hermes, and then you can, for example, automate your research with the Grok API, right? Sorry, the Grok OAuth. So Grok can do like Twitter research and that sort of thing. So as an example of that, if we have a look here, it actually, what I can do is I can go inside the chat here, and I can say, okay, go off and search X, or search Twitter for everything that's just trending about this topic, right?

And it'll actually go off and do it for me. When it comes to generating product pages, yeah, you can get the Shopify CLI, right? Let me just find this here. So there's a Shopify CLI for this that's pretty good.

And that basically means that you can link this inside your agent operating system, or you can give it to Hermes agent and install it. And basically that means your agents can speak directly to Shopify and post content for you and that sort of thing. So it's pretty cool. For research, Grok is great because it can search Twitter directly.

Image generation, you can see here, for example, if we have a look at image generation inside agent operating system here, we've got a studio set up so we can generate images just by describing what we want over here. So that's a really good way to do it. So again, like from what I can see in terms of what you want, probably the best thing you can use here is Grok 4.3. And the same for video generation, you can do that with Grok 4.3.

If you need longer videos, then I would install something called HyperFrames, which can generate longer videos using open source GitHub. Also, I wouldn't recommend trying to do this all at once. Just do one thing at a time. Could be one automation per week, et cetera, just so you don't feel overwhelmed.

And you can grab the agent operating system over here. So that's it. And just to recap, if you're Ecom, video generation, and everything else, you probably want Grok 4.3. You could use, for example, OpenCloud Core and Hermes, but if you don't have this set up, I would just keep it simple and start with Hermes as well.

That's basically it. All right, next one. So Michael. Michael said, I'm glad I found this group.

I'm looking to take my business to the next level. My short-term goal is to train a Hermes agent to be my real estate team's VA, then build out a marketing team, deal with content, et cetera, right? Lastly, working on SEO optimization. Not sure if I should be using one Hermes agent to do different tasks or if I need to set up a separate Hermes agent.

So if it's like the first time that you're doing this, I wouldn't recommend creating multiple Hermes agents, right? I would just focus on one at a time. And then if you really feel the need to have separate specialist agents, you can, but I think it will make it too complicated for you in the beginning. So you can always come onto that later.

Then, for example, automating VA tasks. I think that probably is the best thing to start out with. From there, you can teach it more marketing skills. So after that, you could teach it, for example, video generation, or you could teach it, for example, SEO content generation, and just stack it out.

And again, don't try and do it all at once. Just go with something simple, one thing at a time, one automation a week. If you do one automation a week this year, then you've got 50 new automations per year, which is pretty insane by anyone's standards. So that's how I would tackle this task.

Let's take a look at the next one. So Zayad was saying, which one is better, Hermes plus Grok or ChatGPT? That's a great question. So it depends what you're gonna do with it, honestly.

Really depends what you're gonna do with Hermes. But I would say the Grok is better. And I've actually found the Grok is faster to reply. It works really smoothly.

I've never had any problems ever since I've set it up. And also it can do a lot more than ChatGPT. So ChatGPT OAuth is useful, for example, for generating images or for example, generating replies. But Grok 4.3 can search Twitter, which is great for research and content creation.

It can also, for example, generate videos. It can generate images. So there's a lot more you can do with Grok. And also Grok, from my own experience, has been a lot smoother to implement than using ChatGPT.

So I'd go with Grok, personally. Next question. So for stuff like this, Meher, it's a great question. I would say, number one, don't give Hermes or any other agents anything that you're not comfortable with.

Number two, I just run it locally so that it's basically sandboxed locally. Number three is you can limit what it has access to. But I think the main thing is keep it simple. Don't connect it to anything that you don't want to.

I've not seen any issues from anyone, but yeah, that's the way that I would look at it. And also if you're not sure, don't do it. You can just watch my stuff instead, right? You can watch my tutorials and learn from me instead if you're not sure.

Next up, we got question number four, which is onboarding for Hermes, right? For Hermes agent. And basically he asks, looking forward to some more cool ideas. I've been using OpenClaud and Claude for the past four months building workflows, reasoning, et cetera.

Built everything on Opus and now implement this on it. But as the automations get more complex, you get a variety of errors, right? And he asks, does anyone have any experience with using Noose Research with Hermes? So I actually set up Hermes via OAuth with Noose Portal and it was really good.

You can actually test out and just see how you feel about it. Overall, I found that Hermes is much smoother to use than OpenClaude. And I think the majority of people who have tested out Hermes and OpenClaude regularly over a long period of time have got much better and smoother results with Hermes. And then also what I would say here is you can use a lot more APIs with Noose Portal.

So if you sign up to Noose Portal, you can set up free APIs, like for example, Step 3.5 Flash. They also, for example, had Quen 3.6 for free for a little bit. So they're always bringing new APIs into there. So it's a pretty good way to use it.

And also, obviously, Noose Portal created Hermes. So if you're using Noose with Hermes, it's always gonna be a lot smoother than using, for example, like Claude with OpenClaude, which, you know, OpenClaude, Claude have literally come out and said, we don't want you using Claude with OpenClaude. So it's a lot smoother to use a portal that is literally built for an agent, which is what Noose Portal have done with Hermes. Matt says, thanks, happy to help.

Thank you very much, sir. Olga, Codex in the browser, cloud or not? So Olga was basically saying she downloaded Codex app, did some work in it, but was not very comfortable because it wouldn't access the network. And she was asking about ChatGPT in the cloud.

Does it still work? So she was saying when she clicked on this link here, it asked her to download the app. So if we actually go here, I actually checked it earlier today for you, and I could still use Codex in the cloud. So if we go over here, we'll click on this, and you can see here, I can still use Codex in the cloud.

So maybe it's location variant, or maybe it depends what plan you're on. So for example, we are on the pro plan, as you can see here, and this is a personal account. I don't seem to be able to, yeah, I don't think I've got access to the other workspace, but I can use this one directly, and it works with Codex. This works for me, pro account with Codex in the cloud.

Let's see what questions we've got here. How to connect Hermes agent on VPS? Yeah, so for example, to your PC directly, I think, so basically like you're trying to access your PC, but you've got VPS set up with Hermes agent, right? That's the way that I understand your question.

If that's the case, then you can use something called TailScale, and TailScale can connect remotely to, for example, your other device. So if you have two different devices, your VPS and your PC, then you can connect TailScale from the VPS to the PC, and that's how you can connect them together. All right, Sachi asks about what's the best skill for this, right? What's the best creation skill for this?

Here's the way that I do it, right? And it's really simple. It's a little prompt that I use, as you can see right here. And if I'm trying to create something, usually I look at what works before and then use it again, right?

So as an example of this, if we type in this prompt, as you can see, and let's say, for example, I'm trying to create a variation of this. Let me give an example, right? So let's say I'm trying to create a variation of this. I can plug in this prompt and generate multiple different versions of that, right?

And that just helps me create these really quickly. And then I also, for this prompt, I use something called TextExpander, and TextExpander allows me to just paste in that prompt really quickly. So if I type in this, you can see that it just pops up, right? And then I hit enter and create it from there.

So that's the way that I do it. And then that'll take a little bit of time to generate, but that'll create some nice versions in a second, which we can come back to in a minute. All right, I think this is the last question, which is from Jerry, and it's actually a win. So Jerry actually said that he's hooked on Hermes, right?

He basically set up an automation, pulls in new transcripts every four hours, and then it catches his ideas, his design thoughts, his client notes, supply reminders, right? And instead of them just letting sit in a nap, the agent actually takes it and then starts using that to save it to his Obsidian vault, right? If you're not sure what Obsidian is, it's like a second brain full of knowledge, as you can see right here, where we link everything together and we have notes and memories and context and everything. So that's what he's doing.

So basically, anytime he has new voice notes, he'll plug that into his Hermes agent, and then it goes off. And he said, there's no way I could have tackled this without the confidence I've gotten from there, apart from boarding. Can't thank Julian Gordy enough. So well done, that's amazing.

Like really awesome to see people win like this. And also the thing I would say here is for anyone watching, we can all do this. If you're watching, you've never used AI before maybe, or you're not sure about using AI agents, or maybe you just feel behind with AI, we all do. That's okay, right?

But you can see here clearly that this is an awesome use case and this is an awesome way to use AI and you can do the same, there's nothing stopping you. Awesome. All right, so we've answered all the questions on Hermes agent. Just coming back to this as an example, you can see that we've generated this using the system that I just showed you above.

We've got loads of systems like this inside the Air Profitable Boarding as well. We've got the full Hermes agent dashboard if you want mine. As you can see, so you've got the agent operating system here. You can see when it was last updated.

You can get the zip file over here that's newly updated every single day. And that's all inside the Air Profitable Boarding. Plus I answer your questions with tutorials daily like this when people have questions, when they need help, et cetera, I can help you. And also inside the calendar, you can jump on weekly coaching calls.

Inside the classroom, you can see all of my new daily trainings. We have new daily updates all the time. And then also inside the map, you can get access to people in your city, right? So you can meet up and meet people and connect with people who are doing similar things to you.

And this is all inside the Air Profitable Boarding. So thanks so much for watching. Hope to see you on the next one. Cheers, bye bye.