Hermes Agent OS: Mixture of Agents + Hermes Oracle + Obsidian!

**Julian Goldie** (0:00)
Today, we are going to be running through the agent operating system that I've built, some of the top questions I get on it. I'm gonna help you as much as I can on this sort of stuff. And I've built some absolutely amazing stuff into this recently. I wanna talk you through exactly how we built all these different, basically, I mean, these are some of the best responses I've ever seen. And this is using a new feature we've just added called Mixture of Agents from Hermes Agent, which is pretty wild. We also got the Hermes Oracle inside there, we can pull in the latest trend in news and grab it straight away. We've also, for example, got a lead generation system in here for managing our emails, doing average campaigns, generate leads in whatever niche we need to. And then we've got things like the Memory Galaxy that gives all of our agents contact straight away. We also have a music agent over here, we have a video agent that can generate amazing videos. We've also plugged in open montage, we can generate like basically cinematic AI videos, as you can see.
And these are all powerful systems that we've plugged into the agent operating system to automate and build anything that we want. And so what I'm going to do today is just answer some of the top FAQs from the Air Profit Boarding community, because I know if everyone else inside the community is asking questions about these agent operating systems, you probably have the same questions too. So I'm going to get straight into this and talk you through everything that we're using. So quick one from Lewis. Lewis was asking about like custom agent builds. Do we do that inside the Air Profit Boarding? We actually do. So we have an option for agent requests and it's just a thread you can post your request on. There's no limit to that so you can just post whenever you want. And as long as we don't already have the agent build, then we'll build it for you. If we do already have it, then we'll point it directly to you. Next question from Danish. So Danish was saying, you know, the agent OS pipeline, the SEO pack, which is down here. This basically allows you to like generate and automate SEO with all the systems we've built in. We've just added open SEO inside there as well, which is pretty cool. So that can do your keyword research for you.
It can do rank tracking for you, all sorts of cool stuff.
Now, if you want to do an OK, do you need Hermes to use this?
Well, basically, you can use anything you want.
Whatever API or CLI you prefer to use in this, you can. So you just ask the agent when you set it up to use that particular API or CLI. So for example, if I want to use Claude CLI instead of Hermes for the SEO section, I would just ask the agent that built it to set that up for me instead. So it's really flexible depending on what you need. The cool thing about this is we can grab keywords from our Google Search Console. We've got a free SEO tool for managing everything here. We can generate content and publish it directly to our websites. Then we can actually get SEO traffic using the system, and it's working really well. Let me show you a couple of examples. So these are some of the websites that we've set up using this system. Here's one, here's another one, and here's one more. And you can see the trajectory of all of them. They've gone from zero to hundreds of clicks per day. So it's a really powerful system that's working for us right now. Now, another question from Danish is how can you feed Obsidian memory to Hermes? So because Hermes is set up locally and so is Obsidian, you can just give the local directory of Obsidian with the documentation about Obsidian from their website directly to Hermes and then that will plug it automatically into Hermes for you. And then you can say, okay, every time I use you, please update the Obsidian memory or once a day, consolidate all of your memories and plug them into Obsidian as a new daily log. So just give it the local file directory. And then for the section where you say, you know, do I have to specifically say whilst building the article writing function to use Obsidian memory?
Yeah, I would if you can. So I would just say like, listen, every time you create content, personalize it to me and make it unique to me with my unique goals, my unique frameworks, my unique case studies using the data inside the Obsidian memory. That way we can add information gain inside our content so that it's the best it can possibly be and unique to us. Great questions from Danish there. Jay was asking about the Agent Kanban and the local engine section. So this is something that was built in where you could use local systems. So for example, like this morning, we set up Qwifos, which is a new model that you can run locally with your AI agents. You can see examples of it working right here. So the way that you can fix this is you can just give the details, whatever local model you prefer to use to the agent that set up Agent OS for you and just say, hey, use this model instead or use that model or every time I install a new model, change the default model to that new version. And this way, it's easy to swap and interchange between whichever local models you prefer to use. Another question we were asked was about free-clawed code and omni-root. Now this is not something I've tried personally. I've just taken a look at the example here up here. I mean, you can use whatever you want. I think there's many different ways to use whatever model you want inside Claude code. For me personally, we just use the free-clawed code GitHub, but you could swap and replace it with whatever you prefer. So if you find like a GitHub setup that you like, right, okay, I prefer that setup for free-clawed code, then you can plug it in here. So personally, I've not used it, but feel free to test it. And if you prefer it, you can swap it in and out. The thing I would say here is there's many ways up the mountain. So whichever way you prefer, feel free to customize it as much as you need to. We've got a question here from Momodou about OMI. Now OMI is what we use to basically update our Obsidian database. So what this does essentially is it takes notes on me all day. It's like listening to my conversations, it's watching what we're working on, et cetera. And then we have a bunch of memories that it creates daily. So for example, if we have a look at memories here, it's literally looked at what I've worked on recently. So we worked on working on Goldie Bench and AI Model Leaderboard and then it's taken notes on that. So it's constantly giving Obsidian more context. And then if we want to export that to Obsidian, we can go to more here and we can easily sync this to Obsidian like so.