--- title: '5 Best Use Cases for Hermes Agent in Your Agent Operating System' source: 'https://youtube.com/watch?v=vmMiKxGcFSM' video_id: 'vmMiKxGcFSM' date: 2026-07-14 duration_sec: 0 --- # 5 Best Use Cases for Hermes Agent in Your Agent Operating System > Source: [5 Best Use Cases for Hermes Agent in Your Agent Operating System](https://youtube.com/watch?v=vmMiKxGcFSM) ## Summary The video demonstrates how to build and use an Agent Operating System (Agent OS) to automate business workflows using AI agents like Hermes, Claude, and local models. It covers five key use cases: news aggregation, lead generation, video creation, SEO content, and quality control via loop engineering, all within a unified dashboard. ### Key Points - **Introduction to Agent OS** [00:00] — The host introduces the Agent Operating System, a unified platform to manage multiple AI agents (Hermes, Claude, etc.) for automating business tasks like outreach, news monitoring, and content creation. - **Hermes Oracle for News** [01:30] — The Hermes Oracle pulls trending news, grades it, and suggests content angles. It runs autonomously every 24 hours, logging everything into the memory system. - **Lead Generation Machine** [03:00] — A lead generation tool within the Agent OS finds prospects, drafts personalized emails, and manages campaigns. Users approve before sending, saving hours of manual work. - **Video Agent** [04:30] — A video agent creates full AI avatar videos with B-roll, script, voiceover, and avatar from a single prompt. It uses Hermes with Remotion and Hyperframes. - **SEO Content Pipeline** [06:00] — The SEO tool pulls Google Search Console data, identifies keyword gaps, and generates optimized articles. It deploys directly to websites via Netlify, resulting in 278 clicks per day from zero. - **Loop Engineer for Quality Control** [07:30] — The loop engineer defines a 'definition of done,' then a builder agent creates work, a judge agent evaluates it, and the loop iterates until quality passes. No manual prompting needed. - **Running Agent OS for Free** [09:00] — Five methods to reduce costs: free local models (e.g., Qwen 3.5 27B), free APIs from OpenRouter, existing CLIs (e.g., Claude, GLM 5.2), token optimization with Headroom, and free memory using Obsidian. - **Multi-Agent Orchestration with Kanban** [12:00] — The Kanban board allows running multiple agents concurrently without freezing. Tasks are delegated to sub-agents, scaling productivity across boards and profiles. ### Conclusion The Agent OS centralizes multiple AI agents into one dashboard, automating lead generation, content creation, and quality control. By using free models, APIs, and memory systems, users can run powerful automations with minimal cost. ## Transcript Hello peeps. We're going to get this started. Going to build out some new features inside the agent operating system. Cover some Q&As as well. Do a bit of AI SEO. It's actually one new GitHub that I want to test out. It's called Orca and it's designed for working with a fleet of parallel agents. We'll be having a look at that um and also testing out some new stuff. So, let's get straight into it. If you got any questions, feel free to ask as well. Always here to help. Good morning, Matt. I'm doing fantastic. How are you? What are you working on these days? Nice. And that's it. You got to go for a walk. It's good to stay active as well. But just making some tweaks to the agent OS. Very nice. Me too. Oh, I've got this again. I've seen this this morning. Claude struggling again. Heat. Hey Heat. You inspired me to do amazing things and it's really started out. Oh, thanks so much. I appreciate that. It's good to hear. That's what we like. Thanks so much for sharing. Heat. Heat. That means we've got a new camb update. Apparently, you can run like a thousand different models at once. Something like that. I'm just looking into it. It's pretty fun though. What are some good use cases for this? Hey hey hey. Yeah. So, uh I've not really talked about I mean All right. So the question here is have you talked about harnesses and the designing harnesses to use the ever evolving models available through open router to build swarms. So if you look at our agent operating system and the stuff we've got out there like we we combine all the harnesses together. So for example like Hermes Claude CLI GLM etc. uh even paperclipip for example, but I've never really talked about designing your own just because I felt like I've not really seen anyone design a really good agent harness that's better than what's already out there. But if you do have examples of something someone's created that's genuinely better than what we already have, I'd love to see it. Reox is here. Hi Julian, thanks so much for joining. We're also going to be talking about how you can use an agent operating system for free. I'll talk about some examples of that in a second, too. Uh yeah. So for me I don't use TUI right there. TUI is pretty bad. That's why we have the agent operating system so that you can visualize everything in one place. So for example, let me share my screen here. Like if you're using the terminal, right? of course it's it's not going to look good. So if we open up the terminal here and let's say for example you were using Hermes inside the terminal sometimes it doesn't even work and you know let's say you got claude inside another tab you can't really do multiple things you can't see your history you can't see what you've created very very difficult to manage whereas if you have an agent operating system like this you can see everything in one place and you've got all your harnesses and all your projects visualized right which is way more powerful so for me personally I don't use TUI it sounds like you're not keen on that either. And so I'd recommend a system like this instead because it's way easier to organize everything. Everything's just a click away and it's all inside one place. Like if we want to do outreach, we've got the lead generation section here. If we want to get the latest news, we've got that over here, right? If we want a voice activated agent, we've got it over here. So that's the way that I look at it is like how can you set up a system where you can have everything in one place and it's super easy to use and and that's exactly what we've got right here. So I I wouldn't call this a harness, but it's just like an Asian operating system where all the harnesses are combined and you get the most out of everything. Ah, glad that helps, Phil. Thank you. Am I on a treadmill? I am indeed getting the steps in. Yesterday got 27,000 steps in. So, let's see how we do today. Am I doing a test? Yeah, we're going to run some more tests on local models today. And also GLM 5.2 versus Opus 4.8. Run some tests on that. See what we get back. Heat. Heat. I I don't really uh use GitHub in that way. So, it's not it's probably not something I'm like the best person to ask on that. For us, like when we create something, it's usually not open source. So for example like our agent OS is not open source. It's just for a profitable board and community members. So in that way we don't really do that. Can you talk about something that's actually useful like an actual use case here for a business for example and then actually create it? Heat up here. Hey, hey hey. Heat. Heat. Hey. Hey. Hey. Uh so the question here is have you been able to figure out how you can use a specialized skill to look at your current wiki? See if there are ways or methods of maybe using better ways to um organize it. So for us like our our memory system with Obsidian is is really well organized already. Like we've got a full memory galaxy. Everything is logged and updated automatically inside our agent OS. Like even for example, we've got daily uh logs like so. And so it's all automatically updated autonomously anyway. And then if we need to search for any memories, we've got that and all links to Claude and Hermes and everything else. So when it comes to organizing it, it's already very organized. When it comes to updating it autonomously, that's already set up. And then when it comes to the agents using it autonomously, that's already set up. So we already spent a lot of time automating that and it already works as a system inside the agent OS already. So I think unless it was necessary, you know, there's no point trying to fix something that's not broken. That's the way that I look at it. If already runs very efficiently, why would you need to to change it more? Welcome here. Heat. Heat. How you feel? Hey hey hey. baby. Hey Heat. Heat. Heat. Heat. Hey hey hey. can you approve the use case you're going to use it for first and then once that's done we can run through it. Also make sure you're using the agent OS to demonstrate anything. Hey, hey hey. But make sure we can see visually what you've created and make sure it's deployed to our website. Also make sure it's using our SEO skill if you're going to do SEO stuff. also inside the guide that you create. Hey hey hey hey. Hey, hey hey. Heat. Heat. Okay. Make sure that you're doing this inside the can. Heat. Heat. Heat. Hey, Heat. Heat. Heat. Hey, Heat. Hey, heat. Hey, heat. Heat. Heat. Heat. Hey. Hey. Hey. Heat. Hey, Heat. Heat. Heat. Heat. Hey, Heat. From what I can see, this is not using your guide skill. And also, the guide should be focused on GLM 5.2 versus Opus 4.8. For some reason, you're focused on the app builder. And also, from Goldiebench. Compare the differences between what you've created. Hey, Hey hey hey. Don't use comput use for this. Use the browser extension. Hey hey hey. Heat. Heat. So today we're going to be answering the latest questions on our agent operating system. This is basically how we combine all of our agents together. So for example, we've got like Hermes and the Hermes Oracle. We've got a lead generation machine over here. We have Claude ready to go. We've got a mission control system and everything we need to win with AI inside one single place. So you've got for example a camban notebookm all synced inside one place. So today what we're going to be doing is answering some of the latest questions that I've got inside the AI profit boredom community because I know if people have questions inside here you probably have similar questions about agent operating systems how to build them etc. So let's get straight into this and answer some of the latest questions. So, we got a good post from Andrew and he was saying like, you know, how he's basically set up the agent OS. He was saying, you know, huge thank you to Julian, everyone here. And basically what he's done is use our agent operating system and then build this himself. But he's also shared like everything he's learned. So some good tips here. Number one like keeping multiple projects separately. So what he actually does is he gives each one of his projects his own little notes and brain and memory so they don't just sort of overlap each other. We do a similar thing where we have multiple different projects, multiple different businesses running inside the memory galaxy. And so our agents, because it's so well organized and our agents actually update it automatically, they can sync between different projects, if we ask them about one thing and then another thing, they know how to tell the difference. And that's a great way to set up Obsidian. Now, if you don't have Obsidian set up already, but you want a memory galaxy like this, basically you can see here, for example, we have a knowledge graph and everything is all like sort of segmented into different projects. So for example, we have people we work with. We have for example uh funnel strategy. Everything is a different markdown file but it's all interlin inside one knowledge graph and I've never had to update it personally. My team does that for me. And so if you're wondering okay like how can you manage multiple different projects or different companies inside an operating system like this? Just build out Obsidian and make sure that you have everything separated but organized and tied together. So for example, one thing you'll see is that for each of our companies like for example AR profit boardroom and Goldie agency number one they have links between them and number two they're colorcoded right with bigger modules. So the good thing about that is that it's easy for our agents to visualize it and see the difference between what are our projects who we working with etc. Right? set. For example, people are colorcoded differently to the way that we color code our projects. And this way, everything links together, but it's easy for your agents to organize between each other. Also, he's talked about mo uh multi- aent orchestration, which is something we've set up with paperclip. So, basically, what you can have here is a team of agents working together. They can orchestrate tasks. You've got one CEO who basically in the org chart will command a team of agents who command their own sub teams of agents. And so the beautiful thing about that is it's easy for your agents. For example, if you got Claude or Hermes plugged into the system, it's easy for your agents to coordinate between each other and make sure that you can get the most out of every agent you have plugged in. We've got another question here from Daniel is asking about like animation and video agents and how do you get them working together? Right. So one thing that you can do is you can use these open source projects like for example we have open montage here. This can create kind of like films as you can see here where you can basically in one single prompt generate a short feature film with AI and the quality of this stuff looks amazing. So that's one way to do it. Another option is that you can use a video agent but you tell it the specific style that you want. Right? So if you want for example more like a animation style video or cartoon style video then you would tell the video agent okay this is how I want it to look like here are the characters I want to use etc and with the video agent you could use that too and also Sheena's given a really good tutorial here about how to use this as well and the models you can use so for example you can use a combination of cling seed dance 12.7 seven to generate your agents together. And if you have a single mission control dashboard with each tool having its own tab like we have with the video and the open montage system here, it's easy to organize and coordinate them together. This is pretty wild. So Robbie shared uh agent operating system that he's built for lead generation and this is basically using our agent operating system but he's made it his own. Right? So if you look at the system, basically what it can do is it can find potential prospects for contracting jobs and then reach out to those prospects once he's reviewed and approved it. Right? So what it does is it finds the quick wins with the project details. Then he approves the details and then they're ready to send as an average system. And so he's basically got he's called it the deal desk which is amazing. It's basically a custommade system inside the agent OS where you can reach out and apply for jobs directly. So pretty insane. There was a really good share as well by David. So David was talking about GLM 5.2 which is pretty much up there when it comes to performing side by side versus open 4.8. But the difference is of course that number one is open source and number two it is a lot cheaper on the coding plan. You get a lot more tokens. So if you've seen GLAN 5.2 it's a really powerful system. We actually compared it side by side and it outperforms Opus 4.8 on many of the tasks that were created. I mean, it can create some pretty insane stuff like like check this out. This is a a full open world game created by GM 5.2. So, it can create real stuff. It looks absolutely awesome. It's very easy to use and you can plug it into your agents which you can't do with Claude. And he's actually talked about how it's now faster if you're using OAM. So, Alarm has had it added uh more capacity for GM 5.2 with up to two times faster responses as you can see right here versus other providers. So, if you need a faster way to use GM 5.2 inside your agent operating system, you can go to OAMA and it's pretty easy to set up GLM 5.2. Like you just make sure you have O Lama downloaded which is free and then you just get the cloud s uh cloud subscription and you can plug it into claude code you can plug it into Hermes agent and it should be faster according to this is actually really good as well for local models great place to find local models and test them out we tested out or if recently pretty good pretty good stuff improving local So, what a good question here from Remy. Bonjour to Remy and they were talking about you know does it still makes sense to learn a master NM or focus on the agent OS which is the best especially if you're running an agency. So if you have a lot of experience with AI and you're comfortable using CLIs or claude code etc then I would recommend just focusing on the agent OS instead of NAN because NA10 is great for mastering the foundations and the fundamentals but it's a lot easier once you understand those to build out an agent operating system that can basically automate anything in a way where you don't need to understand code and you don't need to configure individual modules etc. So for me personally I don't use NA10 that much. I do recommend it for beginners, but if you're beyond that point, just go straight to the agent OS cuz it's a lot more fun and it can automate so much more without having to understand HTTPS or anything like that. also something that's really cool like you see with for example Tim is that Tim is sharing what he's working on how he's building stuff his journey and that's one of the fantastic things about being in a community like this is you can share your journey you can share what you're working on you can look back but also a lot of people can relate to that cuz We've all been on this journey like OpenClore only came out in January and already we can do so much with it. So it's great to see this sort of stuff. Also something that's really smart is basically he can take my tutorials and then he can train his agents. Now this is something that's possible with the new learn feature from Hermes agent. So what you can do with Hermes agent and this is pretty amazing is you can give it a guide. So you can go to Hermes agent inside the chat. You can say forward/arn, give it the guide or details of the tutorial and it will actually learn it and save it as a skill for future sessions. So, it's a really powerful way to train your agents up on whatever you want them to learn. And that could be a tutorial, could be a guide, whatever you want. We have a full tutorial on this over here. So, it's a forward slasharn command inside Hermes. Now, something else that you can do with Welcome Randall. And also we have Aber. Welcome Abber. Thanks so much. Baby baby. Hey. question. Do you have the tutorial to connect Hermes EMVPS to HOS? Yeah. So, if you if you go inside the AR profit room, we have a full setup. Let me actually add the link here as well. So, if we go inside the classroom here, let me go to new daily updates. And I'll add the VPS details here. So, you can grab it right there if you're wondering how to use it with a VPS. And then you can see how John set it up. For me personally, I don't use a VPS. Yeah. So, you can grab it down there. Basically, you can use uh tail scale or you can use cloud flare as well. Two good options there. Thanks so much. Appreciate it. It's cuz I get asked every single day. That's why. So, I literally saved it as a response. I use a a text expander. And then if we have a look, for example, like if we type that in, you can see that automatically pops up with the link. Just saves a lot of time. Would recommend it actually. Hey hey hey. Heat. Heat. feel. Hey hey hey. Hey hey hey. Today I'm going to show you the five best use cases for Hermes agent including for example outreach. We've got the Hermes Oracle that can get the latest news and then create content around it. We have a a voice activated version of Hermes and this is so much more powerful than just using Hermes inside the terminal. So, for example, most people they don't know how to use Hermes or what the best use cases are cuz they're going inside the terminal trying to use it there. But the problem with that is that you really don't get the full power of Hermes agent. So, I'm going to show you exactly how to use it. And this is the way that we plugged it into our agent operating system to combine it in five different powerful ways to get the most out of Hermes agent and make it way more useful. So, let's get straight into this. And I call this the Hermes Power Five, which means that we give Hermes five jobs with one free open-source agent. And it can do all sorts of things. It can get you leads. It can write outreach emails. It can make four videos. It can run your whole SEO pipelines. You can finish tasks to a standard you never have to check. And I'm going to show you exactly how this works step by step. So let's talk about the first one which is the Hermes Oracle. And this is interesting because basically what Hermes can do is it can look through the latest trending news. It can pull in what's trending right now, grade it and categorize it in terms of what's happening. And also because Hermes agent has scheduled task option, we can schedule that task every 24 hours. So you can see for example, this was last consulted 4 hours ago. Now every 24 hours is going to pull in the latest news from X. As you can see, what's trending right now and then on top of that we can also see the categorization of the task, how trending it is, what the news actually is, what angle we could use to create content around that that is personalized to us. And then also we can see all of our published content around that particular topic. So this is an article that we created recently. You can see the full page right here. It actually includes the source of the news originally too which is super useful. And anything that we want to rank for whether that's on social media or whether that's for example publishing SEO content we can create quickly inside this system and it's all operating autonomously without us right the only thing that we have to do is click a button and say publish to WordPress or draft this for the social media content itself. So it's super useful and also everything that it does is logged into our memory system. So every time we use Hermes Oracle, everything created with it is plugged into our agent operating system and then we can see the latest news and everything that we've done with Hermes inside this system right here. So I'll come on to more about how that works in a second. But the point here is that you know every business owner is trying to stay current right now. And the problem is that can take a lot of time researching scrolling searching. Whereas Hermes can run that for you. Radar pulls in the freshest AI news and posts and hands you the short version. Then you can hit consult oracle and if you want to refresh your news, you can grab the latest updates right there. And so it's really powerful because you can open up the radar, you can see what's useful right now. It's actually got the links and the sources of each piece of news and you never fall behind again, right? You don't have to worry about shiny object syndrome. You don't have to worry about getting overwhelmed because in 2 minutes you can read through this news and you've got everything in one place, right? This is something we custom made for the agent operating system simply because it's so useful. It's so powerful. But I hadn't seen anything else like that out there right now. Next up, we have the lead generation machine. So if you go to the outreach section here, what you can see is that we can generate leads whenever we want for any single niche, right? So if we type in whatever leads we're trying to find, the AI will automatically find those leads, give us a list of leads we can reach out to and reach the leads and then also we can send emails to those leads as well. So we can see the full details here. And then if we want to do the outreach campaign, we can get the AI to draft the campaign. And then from there we can see all of our campaigns in one place. We can activate or pause or delete them. We can send the latest batch and we can also manage our inbox and the send inbox from the whole section right here. And so it's basically like a full lead generation and email outreach tool as a SAS, but it's using Hermes as the engine for that. And why would you use Hermes for that? Well, it's more powerful. It's faster. You can automate pretty much everything. Again, all you have to do is just click a button. And you'll notice a trend here, which is like everything is inside one tab inside everything is one click away. And the great thing about that is that anything we need, we can find like instantly. We don't need to mess around here. And so it saves a lot of time. Whereas, for example, can you imagine going into terminal trying to find the skill, trying to find all the details of everything you've done? It would be a nightmare, especially if you were just using the basic chat right here. So, we want to keep it organized. We want to keep it clean. We want it to be automated. And that's why we've got this full system right here of all the stats as well. And this the reason that I built this was because so many AR profit boarding members were asking me to create something like this or how to use Hermes for lead generation. This is by far the best system that I've ever seen for doing this. So you can type for example, I don't know, agency owners in the SEO niche and Hermes comes back with a verified list and a ready to send personalized email already written for every person and then you just read approve and send. Um, the great thing about that is everything's personalized and also you can set a maximum number of emails you send. Plus, you can add your API keys here as well, which is fantastic. Next up, we have the video agent. So, this is use case number three. Just to recap here, we got use case number two, which is lead generation, and we've got the lead generation tool that literally automates every part of the process. Then we have the Oracle which can find the latest news, create content around it, post directly to our websites about it and again it's all automated and it's automatically scheduled every 24 hours. Now the third use case that we have here is the video agent and this can be powered by anything that you want. So if you don't want to use Hermes agent for this or you want to use cord instead you can. But basically what we have here is a full system that one single prompt we can type what we want. Then the AI avatar video, as you can see right here, is fully edited with B-roll, research, a script, a voice over, and the actual uh avatar itself, right? In one single click. And we've created like loads of these videos. They look pretty awesome. This is combining basically Hermes Asian with a free open source called a free open- source skill called Remotion and then also Hyperframes. And so they work together to create these videos. Now the other cool thing about this is if you were using the terminal normally well how would you find everything that you've created for any of these projects for for example for your lead generation for example for your setup with videos or for example the oracle and the content you create around the latest news you can't really see it inside the terminal here but you can organize it neatly inside a workspace using this agent operating system instead and so that's why we created this whole system as you can see and in one single prompt We can just change how long we want the video to be, change whether we want it to be a presenter or a voiceover, change whether we want the B-roll to be generated by Grock or Miniax, and which avatar we want to use for that. And then in one single click, we can start generating the video itself. So, it's pretty powerful stuff because you can basically have a full video editing team, but it's run by agents. It's not run by humans and it's all set up. So, Hermes runs a whole pipeline. You give it a topic, the video director writes a script, picks a voice, and the avatar pulls the B-roll into it and creates a video. So, you don't need to edit it. You don't need the team. Is all set up inside one place. So, you could type, for example, I don't know, create a 60-second explainer on why AI agents are more powerful when they work in a system. And then you walk away, you come back, the video is done. And also, the cool thing about this is it's all using one tool, which is Hermes. So you get the topic, the script, the voice and avatar plugged in and then the finished video. Super powerful stuff. Next up, we have the system that basically takes my SEO content and my SEO data to organize my websites for me automatically. So what we've got over here is basically this can pull in the latest data from any of the websites are plugged in here with my Google Workspace API and my Google Search Console data. So for example, if we have a look at this website, we can select where we want to look over the last 7 days, the last 28 days or the last 90 days. And then once we've done that, we can type in the keyword or the type of topics we're looking for. So let's say for example, we are trying to find relevant keywords to Hermes from all the data that we have. What you can see is it pulls in all the data from my Google search console where we're ranking, how many impressions we get, how many clicks we get, what the average CTR is, average position, and what the page relating to that keyword is. As you can see, super powerful. Now, when we're doing this, we can then click on use topic if you want to generate a new page for that particular topic. So, the way that I would look at this is like if there's a gap, if there's a keyword that I haven't created content around, I can easily create that and just click on use that topic. Now, once we click on use that topic, we can then go to this section. We type in the keyword that we just found. We can type in the case study that we want to use for that particular topic to structure it properly. And then we click on generate five articles. And once we've done that, inside the history tab here, you can see that it will basically create content and deploy it direct to my website. And the great thing about this is I don't need to do any keyword research. The agent does it for me. I don't need to create the content. The agent does it for me. I don't need to quality control it because I already have a long detailed skill on exactly how to create SEO content that Hermes knows exactly how to use. And then also we know that we don't need to log into WordPress or into Netlify or anything like that because the agent can deploy it all for me via Netleify directly with a personal access token. And so it's super simple and easy to use as an SEO content pipeline. You might ask, okay, does that actually work? So you can see, for example, this is one of the websites that we've been creating SEO content using this system. And we literally went from like basically nothing to 278 clicks per day using this system. So it's pretty powerful, pretty amazing. And it actually works, which is fantastic. And you might say, well, I'm not an SEO. Can I actually run this? You don't need to be, right? The whole point is that Hermes agent finds the data for you and creates the content for you using the skills that we've already set up and the systems we already set up. So that is use case number four, which is SEO content. And then use case number five is the loop engineer. So it can finish the tasks. So you never have to check quality to control stuff. So let me show you an example of this. So what we have over here is loop engineering and this is basically a powerful system. It's something that the founder of openclaw talked about recently this year. This is also something that the uh team at Anthropic were talking about as well, which is like you don't need to prompt anymore. And you'll notice from everything that we've done today that we're not doing any prompts. They're all like loops that are running autonomously for us. And so we actually have a loop engineered system. And what this means essentially is that we type in our definition of done. So we tell it a goal. So, for example, create a blog post that's well optimized for SEO or create a beautiful video that looks amazing and is interesting and entertaining. And then from there, we can give it a starting point if we already have the project. If not, no problem. And from this point, we can select which API we want to use with Hermes agent, how many rounds this task can iterate, so how many loops can actually run, and we select an API for the judge, right, to quality control the work. Now what does that mean in practice? It means essentially that we give it a goal. We can say okay go for four rounds on this. The judge says whether it's good or not and on every round if the content is not good enough which is determined by the judge a separate model then the work has to be created again. And so you iterate and you improve the work that you've currently got without you needing to give feedback, prompt or quality control or check anything. And so you can see everything that we built inside the workspace using this system, but it will just basically go round and round. Now we can always stop this at any point and we can also change the APIs or the models that we want to use for this. The point is we can get much better outputs by everything running with a loop instead. And so this gives you a system where you define what done looks like. A builder does the work. A judge marks it adversarily and then it actively tries to find what's wrong and it loops and fixes itself until it passes the actual quality control system which is absolutely amazing when you think about it. So you can set the standard, you can walk away, come back and the work is finished. Now you also might think okay doesn't this use a lot of tokens? But the great thing about this is you could use CLI you already have access to so you don't need to pay any extra. You could also use free APIs or you could use token optimization techniques. So, for example, you could use something like Headroom, which is a free open source project you can use to reduce the amount of tokens you create or um run through for each task. And so, the way this works is you define what's done, the builder acts, the judge marks, it goes round and round until it finally passes the controls. And so, the old way is like, you know, if you before Hermes agent, you were like manually looking to keep up with the news. You were uh writing every email and trying to find leads yourself. You were trying to manage a whole video marketing team or trying to do everything yourself which is even more timeconuming. You're guessing SEO keywords and no data and you checking all the quality um outputs from your AI directly right which is a nightmare in itself and so that is a very timeconuming process. Now with Hermes, each one of these tasks is saving you at least an hour a day, right? So the Oracle finds you the news and you can create content directly from it. That saves an hour of messing around. The lead generation tool writes emails, sends the emails, manages your inbox for you, and finds the leads for you. That saves at least an hour. Then you've got the video agent that can create videos automatically for you. And you have the search console that finds and creates content for SEO. And you have the loop engineer that quality controls everything for you so that you end up with better outputs. And what you end up with is one dashboard powered by tools that you already have access to, but you've just organized in the right way. And that's the the full use cases of using something like an agent operating system. There's actually a lot more inside the agent operating system that were built, but that's just like probably the top five things inside there. We didn't even talk about the voice powered activated agent over here. Um, there's so much so much to this, so much more you can do with Hermes, but there are some of my top use cases for for using this stuff. So, if you want to get the agent operating system that I've set up, you could try and build this yourself. If you want to get uh my setup with all five use cases inside one dashboard using Hermes agent, and you know, everything you saw, the Oracle, the lead generation tool, the video team, the SEO pipeline, the loop engineer, it's all inside the agent operating system. And so, inside there, you get the Hermes power five that we talked about today. You get the agent cambban. You get every CLI that you've already using, but you can plug it into into this system. You get our best token optimization playbooks, so you can reduce the amount of tokens you use. You get our local Hermes engine if you want to run local models, which are free and the loop engineer, claude workspace, memory vault, and 3,900 business owners all inside the profitable boardroom. Right? So, you get the full operating system and access to our community. So that's all available link in the comments description or go to the ariperbond.com. I personally answer every question inside the community every single day with video tutorial and there's always people online 24/7 so you can get help and support whenever you need to. Inside the classroom you can get all of our best trainings. So we actually update this section right here with new versions for the agent OS daily. You can see the last update date. You get video tutorial on how to use it. Step-by-step guide and then the zip file to install it. And each day based on what's actually useful and has relevant use cases, we create new video tutorials if you want to learn the advanced stuff. Inside the calendar, you can jump a week coaching call, share your screen, ask questions in real time. And inside the map, you can meet people in your local area who are building with AI agents just like you. Plus, you can direct message me and ask me any questions personally, too. Thanks for watching. See you on the next one. Thanks everyone for watching. We got two thank yous. Thanks so much. Hey. Heat. Heat. Thank you. Yeah, we have a lot of training on that inside the air for border, too. So, if you're interested in that sort of stuff, we have a full uh step-by-step SP and training guide on exactly how to do it. Plus, you can ask me any questions as well inside there. Thank you. Heat. Heat. Hey hey hey hey. Yeah, something like that. I never thought about that, but yeah. It's a good deal. Depends on the system, depends on what you're doing and what you're uh going with but and and who you're talking to, right? So, for example, if you're working with enterprise, it's going to be totally different to if you're working with like a a small online business. baby hey baby. Hey hey hey. Hey hey hey. Heat. Heat. Hey hey hey. Heat. Hey, Heat. Asian operating systems are super powerful. I mean, you can basically build and automate any sort of workflow that you want inside a setup like this. So, for example, we've even built like a outreach tool with Hermes agent. We've got a voice activated version of Hermes over here. We have a a memory galaxy that's ready to go. We can automate videos in like one single click. We can also, for example, automate and create SEO content and deploy it to our websites in one single click. And this is all inside one beautiful system that works together to orchestrate and manage our agents. However, one thing that I see people worried about all the time is like how can you run these agent operating systems for free or get the most out of them? And that's exactly what we're going to talk about today with the free agent operating system engine. So you can run a whole operating system of AI agents for free forever using a combination of all the different systems that I'm going to show you today. And the thing I would say here is like you know a lot of people uh worried about token usage. They're worried about APIs. They're worried about you know having a system like this but then you know going through their limits on the CLI or their coding plan for the month. And so the whole point of the agent operating system is of course to let it run and automate autonomously. But if you're worried about doing that, then let me show you some ways around that so you can use free models to help you as much as you can. Right? So let's get straight into this. And there's basically five systems I'm going to show you today that will help you either completely run this for free or reduce the amount of tokens used massively. So we're going to break down each one of these as you can see. So free local models, free APIs, CLIs, token optimization, and also free memory systems. So you can plug this into your agent operating system and then you can have these amazing amazing automations, workflows running, but you can run them for free. So let's get straight into this. The first thing that I would say is that you can run local models. And I've tested out quite a few recently. I'll show you what I think is good and what I think is bad, right? And I only have like a I have a Mac Studio. Even then, it's not amazing for running local models, but the best one I've seen so far is the Quen 5 uh Quen 3.5 27B coder. That's been a pretty good one that we've used so far. I can create some awesome stuff. Let me show you an example of something that we built here. Um so this is actually fully built with a local AI agent. We also, for example, created this system um which is is not like I mean it's not frontier level, right? It's not going to be like Opus 4.8, but if you want to run this for free and you you know for most things, you're not going to be creating like crazy graphics or video games. You're just going to be creating a lot of content and that sort of thing. So, if you want to know how to use these, well, you can use a system like I'm showing you right now. And so we have the local engine here and we can plug in free models into this system, free local models and then we can build and automate whatever we want. So for example that game that I just showed you a second ago that was fully created with this system here. And it's the same with free clawed code. You can run local models and you can run free APIs with free clawed code which is an open source project that basically takes your free models and then plugs them into the agent harness which is free clawed code. And so that is method number one which is using free local models. Now if you're wondering okay where do you get free local models from? You can get them from hugging face and also if you're running local models on a Mac then you can also use MLX to run them as well and that seems to be better than uh OAM when I've tested them out personally. They've been a lot faster for example. So that is method number one. And if you want like a local model to actually be useful, you can check out my local model benchmarks that I've tested pretty much everything with. So you can see we've run 42 different tasks for each of these agents. Or is another good one as well for coding locally. And so if you want to see what we've built and how they compare, you can check out Goldie Bench for that. And we've got a local leaderboard for this sort of stuff. Next up, you can actually use and wire in your CLIs that you're already paying for uh for free into the system. Right. Um, and also what you can do here is you can use anything that you're already using inside your agent OS. What do I mean by that? Well, for example, let's say recently I subscribed to GM 5.2. If I've got that as a a CLI, then I can also use that inside my agent operating system. I would just plug in the CLI into the agent operating system and then it doesn't cost me anything extra. And the good thing about for example the coding plan on these open source models like GM52 or Kim K27 the great thing about them is that they don't tend to run out of tokens right you can use them a lot get a lot out of them but you don't need to worry about that so if you've got existing CLIs like for example claude as well you can plug that into your agent operating system too and the great thing about that is you still get the power of an agent operating system but you don't need to pay anything extra so that is method number two which is also free now What you can also do from there is you can use free APIs. So as an example of that, if you go to open router here and you type in free, you'll see loads of different free APIs that you can get access to and you can plug into your agent operating system. So for example, north mini code is a free API that we can get from open router. We can grab a free API key from open router. Then we can go back to Hermes agent for example and we can plug that free API key directly into Hermes agent. So we've actually got a separate profile for our free API key with North Mini code and we can use Hermes agent for free whenever we want. And so all of these workflows for example like the Hermes Oracle or the outreach engine that we've built for Hermes agent you can actually plug a free API into that and use them that way. So that is method number three. And just to recap here, we've talked about using CLIs, we've talked about using local models and also free API keys as well. Also, the great thing about this is for example, if it's a basic task, you could route that to a free local model. If it's like a medium difficulty task, you could give that to a free API. And then when it's a really hard task or something that requires a frontier model, which is not that often, then you can plug it into a CLI that you already own, for example, like Claude or GLM 5.2. But either way, you're reducing the amount of tokens you use. You're reducing the amount of resources required to run an agent operating system. And it's also super easy as well. So I'll give you an example like our Claude plan that we use a lot. We actually built the agent operating system using claude and that comes with a CLI and so you can plug your CLI into the agent OS. It can connect to the whole system. The same with for example if you're if you're already subscribed to Twitter, you can plug in Grock build and you can plug that into Hermes agent. You can plug that into uh the Grock build section over here. And then just by having a Twitter subscription that we already have, I can plug that into my system and build and automate anything that I want. And you know, Grock itself is pretty good. Like it can it can generate some pretty cool stuff as you can see right here. So it's really about just being resourceful and finding ways around things if you're worried about this stuff. If you're not worried about it, then you don't need to to think about it, but a lot of people do ask me this question. So that's why I'm showing you today. Now also what you can do is you can make your existing AI agents way more efficient. So what I mean by that is basically sometimes you can be using too many tokens for smaller tasks without even realizing it. So what you can actually do from here is you can use a token optimization layer like for example headroom that can sit in front of the jobs that you give to your AI agent. Now, if you're wondering how to access the Headroom, you can see an example right here. It's actually designed to cut your token costs by like 50%. Here's the main GitHub. It's actually trending on GitHub. On the research, it's designed to use like 60 to 95% fewer tokens on the same answers. So, what that means is basically if you give headroom a task, a task that you use with headroom might take up 60 to 95% less tokens than if you use a normal sort CLI. So, it's kind of like compressing the amount of tokens that you use with this compression layer. Now, when I tested it myself, I think it reduced it by like 20 to 30%. So, it depends on the task that you give to Headroom and what you're working on, which CLI you use as well, and also what your memory system is like. But that's just another way to use this. And you might say, well, isn't shrinking the context going to make the answers worse? Sometimes it can actually make them better because a bloated prompt buries the actual task under noise the model has to wade through. So if you trim what matters that means the model spends its attention on your real task not on rereading the same context that you have for the hundth time. And so you send less and then you use less and the answer is actually sharper. So that's a really good example. Now the final step and we've talked about four different ways to run an agent operating system for free and reduce the amount of tokens you use. So number one was free local models. Number two was using free APIs. Number three was using CLIs and number four was using token optimization systems like headroom. The final system is free memory. Right? So you can actually use a free memory system. So, for example, we have Obsidian plugged into this system. And let's say, for example, we're using any of our AI agents, whether that's Claude, whether that's, for example, Hermes, Open Claw, whatever. We can use a free app like Obsidian as the memory layer for our AI agents. And that means they all have context. And it means that they can also organize your context for you. And so, if I ask Hermes a question about my goals or my systems or my business, it knows everything that it needs to know about me. in an efficient way. I've never had to organize this myself, but it's it's a pretty amazing layer that I can just plug into any agent. If a new agent comes out tomorrow, no problem. I can plug in Obsidian directly into it, right? And Obsidian is free to use. Just a simple app like this. Literally, all it is is just like a bunch of markdown files organized into folders and then organized properly, right? And every single one of these dots is a dot that links to me and my system, my knowledge graph that my agents can read. And also the great thing about this is it's a positive feedback loop. So your agents update and organize your notes for you every time you use them. So if we go into the recent section here, you can see these are all memories from when I've used my agent. And it's updated every few hours as you can see. And then also it's a positive feedback loop because when I'm using my agents, I don't need to reprompt them. I don't need to paste in context or correct them because they pull out the context from this system. And so they update and organize it for me which saves me time. And then it also saves me time on the other side because when I'm using my AI agents like Hermes, we've got this free system that automatically updates them on everything I've been working on up to the hour. Right? So if I'm if I go into for example Hermes or Claude and I'm like what did I work on yesterday or what did I work on a few hours ago? It can pull in this context and all these memories that we've used to get the most out of the system. And that's how powerful it is. So that is method number five for running an agent operating system for free, right? which is the free memory system and you have your Obsidian Vault with your goals, your clients, your voice and that just organiz itself and you can use free APIs or free CLIs plugged into your AI agents to update and organize it for you. It's a free memory loop. So that's basically the whole system and if you look at like the old way versus the new way for using this, you know, the old way is like every agent is using too many tokens because you don't have headroom plugged in. You might be using loads of different subscriptions but then also paying for the API without even realizing it. You're worried about using your agents who use them less. You have fewer agents, you're worried about the prompts. And also, if you're not using local models and let's say for example, you have data that's private. Well, that would go to the cloud as well. And then sometimes you hit a rate limit and then you have to stop mid build. And the result with the old way is that you've got an agent operating system you're just not interested in using because you're worried about too many tokens. With the new way, you've got a system where you can run it on free local models which are private offline. They can work without the internet. So your agent operating system can actually run offline. You can plug free APIs into your agents as I showed you before. You can get them from open router. You can use frontier level CLIs like Claude and plug those into your system. You can use token optimization systems like headroom to reduce the amount of tokens you use and you've got a free obsidian memory which means your agents don't burn tokens relearning your business. And the result is you can let it all loop and it's free to use. So this pretty powerful stuff. Now, if you want everything that we've talked about today, and just to recap, you stopped and reduced your token usage by 9% of headroom, you got free cloud models with APIs, you learned how to plug your CLI into the system, you learned how to make your agents more efficient, you got a free memory system, and you can finally let it loop and run without worrying about all this stuff. Uh, you can get that inside the agent operating system, right? So, we have this inside the air profit boardroom. And if you want the free agent OS engine ready to go, you can build every piece yourself. Um, but if you'd rather skip it and just run my exact setup, it's all done for you inside the AI profitable. So, you get the full agent operating system. You can you get all our trainings on the best free APIs. You get access to me, so you can ask me anything anytime you need. We've got token optimization playbooks inside there. You get the full zip file and every prompt for building the agent OS ready to go. And we've got loads of members who are using systems like this to get the most out of it. All right, so you can see we've got 194 pages of testimonials from people inside our community, getting the most out of this stuff. So if you want to join us and be part of this, feel free to join. But the main thing I would say is we're all learning and growing together and just building amazing stuff. As you can see right here, it's also super exciting to build an agent operating system. If you want to get that, you can get it inside the profitable community. Just go to the classroom and then go to new daily updates and you can find the agent OS here with a video tutorial, the last update date, the guide, and also a zip file on how to install it. We had new daily guides based on what's actually useful. So if you're interested in local models, we actually did a new test with a full step-by-step guide here on Quable. And if you want to ask questions, I answer them personally inside the community and so does the rest of the community to help you. You can also jump on weekly coaching calls, ask questions, get help in real time, etc. And inside the map, you can meet people in your local area who are building with AI agents like you. And you can ask me any questions anytime you want to. So, thanks for watching. Hope to see you inside there. Link in the comments description or go to the apiproferbomb.com to get access. Beatric for you. I would just have a look at the testimonials here. You can see so many people are absolutely loving it inside our community. So, you know, if you want to see examples of people doing it as well, not just me. You can see all these people here that are building amazing stuff with this. So, yeah, it's really cool. Back in a sec, beeps. Hey, hey, hey. Heat. Heat. Heat. Heat. Heat. Heat. Heat. Heat. claimed exactly at once, right? Because it's concurrent now. And then we're going to have one button that deploys all of them in one single go, right? And so this is the part that the freeze fix unlocks because we can have a team of agents all creating and publishing articles at once or creating videos as well. And then instead of having one agent at a time which you'd normally do inside the Hermes tab here, you can have a team of agents working together inside here. Right? Big difference. You can get way more done with a team of agents. It's kind of similar to Claude and Ultra Code. So if you've come across claude and code, basically you can have a team of multiple agents working together with Claude as the orchestrator and then it delegates tasks to the relevant sub agent working on that task. That's basically how a cam board would work as well, which is pretty nice. And so if you look at the old way, the old way is like running one agent at a time, watching everything freeze, waiting for that to come back to us. The new way is like we can have a team of agents running on one board. Nothing freezes up. every task is completed at the same time and we can scale that up across multiple different boards and multiple different profiles. So these are our agent profiles. These are the boards we've got set up right here. Now you might say as well, okay, doesn't this use up a lot of tokens, but you could use free local models for this. You could use free APIs, you could use CLI you already um use. So for example, we could plug in GLM 5.2 into our agent profiles as well. There's many different ways you can do this, right? And so it's a pretty powerful update. I think it's quite underrated, but the main point here is like the cap on multi- aent work just came off because for a long time the the honest answer was to to like can I just run a team of agents on a camb with Hermes was kind of broken but now it can run a lot faster. It can run on the same board. You can have multiple teams of agents and you can build anything that you want and automate it whenever you need to. So this was one board agent operating system is a whole operation. So what you just saw today is basically one little surface inside the agent operating system. But if you also get our system inside the aircraft boarding link in the comments description or go to the air profile board.com you can basically have the agent cambban. So you can fan one goal across a team of agents. You can have the full Hermes fleet. you get the full SEO funnel that we've ran and we also have like playbooks on how to reduce the amount of tokens to use as well. So we've built loads of cool features like this for Hermes. So for example, we've got the Kambban feature here which is obviously using their feature but we've made the UI nicer and made it much easier to organize and then we've also plugged in some custom workflows based on what Hermes can do. So we have the Hermes Oracle that can find the latest news here. We have uh the Hermes voice activated agent that we can speak to and build real stuff with. Over here we have the studio where we can generate images, videos and voice with Hermes agent. We also have a lead generation a mixture of agent system here so that we can segment all the workflows that you can automate with Hermes but in a way where F is just one click away. So if you want to get that full system it's inside the profit board community and this basically just helping people grow and learn with AI automation. So, if you go to the classroom, go to the new daily updates, you'll find the Asian OS system here, the last update date, the video tutorial on how to use it, full guide, and the zip file to install it. And then we add new daily guides as you can see right here to get the most out of this stuff. Now, you can also ask questions inside the community, and I personally answer them every single day, and so does the rest of the community. So, it's very active. There's always people online ready to help. And then inside the classroom, you can get all of our best trainings, including a complete beginner to expert course here if you're brand new to this. Inside the calendar, you can jump on four weekly coaching calls, get help and support in real time. And then inside the map, you can meet people locally who are building with Hermes and other AI agents like you. And you can connect with me personally. So feel free to join link in the comments description or just go to the aprofitwoman.com. Thanks for watching. All right, peeps. On that note, I am off. Thanks for watching everyone. Thanks for all the great questions. I've answered every single comment, every single question. I appreciate you all. I'll see you on the next one. Cheers. Bye-bye.