How Claude AI Runs My Whole Agent OS

Today, we're going to be answering some of the latest questions about the agent operating system, how to build them, how to use them, how to get the most out of them, and some of the cool things you can do with this stuff. Now, I'm going to get straight into this, but basically, these are questions from our AI Profit Boarding community, and I answer them every single day in a video tutorial like this. No more debt, the members are number two, because I know that if they have those questions, you probably have those questions too. And so if you want to ask me any questions like this, and I'll create a video tutorial like I'm doing right now for you, then you can post questions inside the community, link in the comments description, or go to the AIProfitBoarding.com.

Let's get straight into this. We've got a few questions about Hermes, so we'll kick it off with that. So shout out to Meron. I have several questions that hopefully the community is running to and can recommend.

Number one, how to set up and create the migration processes. Is Docker or Linux instances the best way to start? So number one for this question, I'm not 100% sure what you mean, but basically, if you want to set up Hermes Agent, you can set it up on a VPS if you want to keep it isolated, or you could set up with Docker as well. For me personally, I run it locally, and I don't have any issues.

You can also run it with, for example, like TailScale. So you can have, for example, the agent operating system with Hermes Agent plugged in, and then you can actually have that connected to TailScale so you can control it from mobile as well. And that way, it's on a secure environment via TailScale, but you can still access it on multiple different instances, and you can migrate that instance to multiple different devices. The other option that you have for connecting with Hermes across multiple different places is you can just connect it to Telegram or Discord and control it from your phone.

Question number two, is there a course or template to use if I want Hermes as the top orchestrator and Chrome manager and then sub-agent spawners and Claude as technical architect and developer fixer roles? Yeah, so what you can actually use is Paperclip. The Paperclip basically orchestrates your agents inside a team. So if you want separate agents, maybe one is the CEO, one is the architecture developer, one as, for example, the sub-agent that does all the groundwork, then you can use Paperclip.

Now, Paperclip can come in two different formats. So we have it inside our agent operating system, but then you can also use just a standalone GitHub project for that as well. The other thing that I'd say is that Hermes now has a delegate tool, which means it automatically spawns sub-agents for you. So you don't even need to manage them yourselves.

If you're just using Hermes, it will automatically do it for you when you ask it. Last question, which is also, would having a Hermes master agent with separate profiles in each environment or separate instances in local machine and master orchestrators outside the spawn sub-agents in each environment work best? Complicated question. So for me personally, I will keep it as simple as I possibly can.

Now, if you wanted multiple different Hermes agents working together on separate instances, all in the same environment, you could just have like a Telegram group chat or you could have a Discord group chat with all the Hermes agents added in. Or you could, for example, even use something like Buzz. So Buzz is a new free open source app from Jack Dorsey. And that basically allows you to add other humans and other instances of other agents.

So you could have them all working inside one environment. But again, for me personally, I like to keep it simple. I just wouldn't do that because I think it's complicating something that doesn't need to be complicated. Now, we actually got a question about the setup of our agent OS.

So, for example, let's say you're using Hermes and let's say inside the studio we've got Minimax and Grok set up, but you don't have Minimax or Grok and you don't want to use them. So when you set up the agent operating system using the SID file, you can ask the agent that sets up the agent OS for you to use different models or images or anything else that you're creating inside there. And literally all you do is you ask the agent to swap it over and then test it and make sure it actually works. So this way, the agent, for example, like Claude or Hermes or whatever agent you use to set it up, does all the hard work and the testing for you and the technical stuff.

And then you just actually make sure it works and give it feedback if it doesn't. Look at what you spend your time on and then work backwards from there. So anything that you're working on day to day, you can use AI to automate it. That could be, for example, marketing.

I'll give you an example. Let's say, for example, you have data analytics. What you can actually do is set up a scheduled task each week with either Claude or Hermes and ask it to analyze the data, give you some beautiful charts and also give you some actionable tips based on it. Or, for example, if you have a lot of data like this, then you could ask it to create a weekly report that analyzes the data, breaks it down into charts, shows you what's working and what's not.

And then also gives you some ideas for interesting automations you could build based on that. Those are some of the ideas I would go with. We have some interesting questions from Christopher, who's asking about how to use the AgentOS in four different ways. So number one, his first question was how to give agentic OS clear ongoing instructions.

So with the actual AgentOS, all the workflow is kind of built in and then you can customize them how you want. So there's not many instructions to give unless you're, for example, directly prompting Claude, but a lot of the systems inside here are just ready made and ready to go. And you can create any new ones you want to add as well. So that means that you don't really need to give many instructions.

However, when you're setting up, so let's say, for example, you use Claude code to help you set this up, then what you want to do is just make sure that it tests anything that should be working and fixes anything that isn't working, but you want to work. Right. So if your section and parts of it aren't working, then ask Claude, what isn't working, fix it and test it and keep going until you finally do fix it. And that's usually what I do.

If anything, it's not working. So I'll give you an example. Like earlier today, there was something that was not working inside my AgentOS. I said, why is it not working?

And then it just came back like four minutes later and was like, it's fixed now. So the great thing about this is that any problems you have with the AgentOS, you can just fix it automatically by going straight to your AI agent. The next question was how to automate SEO and GEO tasks through SEO office. So for anyone who's not sure and is reading or watching this, the SEO office is a free plugin for SEO, which gives you loads of skills.

And so again, if it's not working or if you have any issues set up, go to Claude or the agent that you used to set it up and ask it to fix it for you. But you basically can use it kind of like a team of AI agents, each of them are specialists in that particular topic. Now, one thing you do need to give it access to is data for SEO. Data for SEO is the API you want to give it access to.

So that has access to data in terms of rankings and that sort of thing. And then whatever you need to automate with SEO or GEO, you can plug into the system. So, for example, if you need to create content, well, there's a content orchestrator inside there. If you need to, for example, do keyword research, there's a keyword research agent inside there.

So I would just look at, OK, what do you spend your time on when it comes to SEO? And then whatever you do spend your time on, I see agents pre-built inside SEO office to do that for you. The next question we got was how to connect task triage to Kanban and the AgentOS. So for this system, and this is the Kanban board.

So for this system, you just connect Hermes and it uses the built in Kanban features inside Hermes. So if we have a task that we wanted to do, like, for example, yesterday, I was using OpenCode with it to build stuff out. If we have a task that we wanted to do, we can just plug in the task into that system and ask it to create it for us. Now, if the agent doesn't respond or if Hermes doesn't respond or anything like that, then just go back to your AI agent that set it up and ask it to fix and test it until it is fixed.

And you can also give it the documentation on Kanban boards from Hermes websites and ask them to fix that for you. But that's basically how I connect them. And the final question was how to connect or create a Kanban workflow. But that's basically the same as question number three.

So see answer above. So that is basically it for all of our questions inside the AI Profit Boardroom. I've answered every single question and I do that every day for you, my friends, just to help you as much as I can. And if you want to ask me questions like this and I'll create a video tutorial for you, feel free to check out the AI Profit Boardroom and then just post inside the community.

Always happy to help. Inside our AgentOS, we're adding new features daily. You can grab the full zip file to install it inside the classroom. So go to the classroom and then go to new daily updates.

And then from here, go to the AgentOS system and you can grab the full video tutorial, the zip file to install it. And you can also get our new daily tutorials every time something useful comes out. Like, for example, yesterday, I set up tail scale so I can control the AgentOS from any device or any laptop. Then you can set it up inside here and we give you the full step-by-step guide and video tutorial.

Same for DeepSeek. That dropped a couple of days ago. We've already got a full masterclass on it. Same for Buzz, right?

And then also inside the calendar, you get four weekly coaching calls. You can get help and support in real time. You can ask questions. You can meet other members on a live Zoom call.

You can ask the coach any questions as well. And then inside the map, you can meet people in your local area who are building out with AI agents like you. So feel free to get this link in the comments description or go to the AIProfitBoardroom.com. You might also say, do you need to be technical to use this?

Or I'm not technical enough to set it up, etc. Personally, for me, I'm not a technical person either. I don't code. I can't write HTML or read HTML or anything like that.

But you don't need to be an expert in any of those things, right? Like so many people are getting amazing results with the AI Profit Boardroom and they're non-technical people, right? So if I'm non-technical and I can do it, and for example, Andrea can create an amazing mission control system and get amazing results of it. And we've got 207 pages of wins and testimonials.

That I know you can do this too, right? You don't need to be a technical person to get the most out of AI. In fact, sometimes technical people overcomplicate it too much. So I'll see you inside that link in the comments description or go to the AIProfitBoardroom.com.