Hermes Agent VS Odysseus: Who wins?

Odysseus AI Agent VS Hermes Agent Who wins. So today we're going to be testing them out side by side. If you weren't aware already, Odysseus is the new AI agent that's just dropped from PewDiePie this week and it is like an agentic operating system as you can see right here. So you've got an AI agent but it's built into a full UI like and today we're going to be testing them side by side. So seeing who outperforms whether it's Hermes or whether it's Odysseus, which one is the best. Now if you've never used this before, you can get access to Odysseus. It's free and open source and you can just follow the setup instructions here. If you've not got the technical expertise to set up yourself, no problem at all. You can actually just get Claude Code to set it up before you just give it the GitHub instructions. And these are two different open source AI agents. Now we ran both, testing them out side by side. And here's what I would say is that Odysseus is a polished single app you run and manage yourself. Now Hermes is a standalone AI agent. You can run it inside a desktop app like you can see right here or we've actually plugged it into our agent operated system. That's one of the first things that I would say is if you look at the way Odysseus is set up, really it's designed to just be used alone, right? This is not designed to be set up and used inside a system where all your AI agents orchestrate together. It feels like you've got an AI model underneath and this is more like a workspace where you can use an AI agent, which is Odysseus. The other thing that I would say here is when you're using it, one thing that I found is like it's a little bit messy, for example, when you're using the UI. So for example, if you're using Hermes agent, it's going to be nice. It's going to be clean whether you're using that in the terminal or inside the agent OS. You can keep everything organized. Whereas, for example, if you click on the email section here, you can see that actually comes out in a pop up. The problem with that is like if you're switching between all these different tools, like you can quickly have three or four different pop ups layered on top of each other, which is not that useful. Additionally, the other thing that I've seen between both of these is that if you actually look at the brain, the brain of Odysseus is built into the app. And what I mean by that, for example, is if you look at Hermes agent, they've designed it so you can plug like any sort of memory system that you want into it. Whereas if you look at the memory section and the skills inside Odysseus, you can add memories manually, but you wouldn't link this directly to Obsidian. You can import stuff, you can import your Obsidian, but it's not going to be linked live. So, for example, if you look at Hermes agent, they've basically focused on having whatever memory you want to plug in there. It's optional and it's configurable. So you can basically plug in different memory. They have a full setup for the memory status here. Whereas if you look, for example, at Odysseus, it's more like something you type in and then you manually import stuff. So it's not like a living memory that you share across all your AI agents. And that's the other thing that I've noticed as well. For example, if you look at Odysseus, it's really designed for people who just want one agent, one place, everything stuck in. If you look at Hermes agent, it's basically something that can be orchestrated across multiple different AI agents. It's designed to work together with different ones, right? So, for example, if you're using an agent operating system or you're using, for example, Paperclip, Hermes agent released a add-on for Paperclip so that you can integrate it with other AI agents. If you look, for example, Odysseus, it's more designed to just be used in isolation because, for example, the brain that you plug in is not shared across multiple agents. It's just really plugged into Odysseus directly. It's one standalone app. It's not designed to be configured with everything else. It just feels like something that's totally isolated from everything else. Now, the other thing that I've seen here is it seems to be designed for using local models inside Odysseus. Whereas Hermes agent, obviously they have a news portal. You can use free APIs. They just released another one today, which is news portal with Nemetron 3. So they've partnered with them. And so, like, the actual memory system that you plug into Hermes is designed to be usable for anyone who's running local or cloud-based models. Right? So you can configure and you can have API keys for OpenRouter and OpenAI and everything else. If you look at the setup for Odysseus, it's really designed for local models. So if we scroll down here, you can see that all the models in the list, so this is a cookbook where it recommends models, they're all pretty much local. Right? And it even grades which models are the best based on your setup, which is very useful if you're running local models. But at the same time, it feels more like they're trying to make you use local models, not cloud-based models. Whereas, for example, if you look at Hermes, they've really optimized the onboarding. If we go to the manage section here and then we select between models, they've really designed it for multiple different models in the cloud. So it's a lot easier to integrate models across different systems, different platforms, etc. In terms of the actual responses for like just general day-to-day stuff, it performed pretty much very similar when we plugged the same model into both. So we tested out with Gemma 4 inside Hermes and Odysseus. Hermes was a little bit more in depth, but I would say there was no big difference in terms of like general day-to-day responses. But what I will say is that if you're using the UI of Odysseus, it's not that customizable. Right? This is what you got. This is what it comes straight out of the box with. This is a UI they recommend. Right? Whereas, for example, you can really customize Hermes in the way that you want it. You can basically have Hermes underneath as the agent and the hands doing the work. And then inside Hermes directly, you can customize it exactly how you want. For example, we built out a live voice agent. We've got the studio here. We've got it integrated inside the mission control. It just feels like something that's designed to be molded exactly how you want. But I do think Odysseus is useful. Right? I think it's more for like people who are just getting into AI agents and just want to test something. And also specifically for people who are looking to run local models with their AI. Maybe they don't want to use it or they just want to keep everything local and private. Also, if you look at the way Odysseus is built, like they have specific sections for calendar. For example, for email. And so it really feels like Odysseus shines if you just want one tidy app. You like its built-in email calendar. You want a cookbook for local models. You enjoy self-hosting. And you're happy with a team of one AI agents. Whereas, for example, Hermes shines if you want it working 24-7. If you want many agents working together. And also if you want it running in the background 24-7. Bear in mind like Hermes, it has a background setup. What that means essentially is like it can run 24-7 even when I don't have it open inside the terminal. Right? Even when I'm not hosting it locally. And the final thing I would say with this is if you look at Odysseus, the actual AI will come and go. Right? So for example, the systems and the agents we use today, totally different from six months ago, 12 months ago. There are AI agents that we don't even think about anymore. Why is that? It's because this industry moves so fast. And so if you look at Odysseus, it's a really cool idea. Great app. But if it's just an AI agent that's standalone in its own sort of isolated box, which is with this UI. Then the problem is that in six months when something new comes out, the AI agent will be replaced. Whereas if you have an agent operating system like this where everything is plugged in, you can swap and you can change depending on what you use today. So that's the difference. It's like, for example, Hermes is designed to be put into this agent operating system. Whereas Odysseus is a system already. You wouldn't plug it into something else. It's its own standalone app. With its own UI that isn't really moldable. So that's my comparison between the two. The final thing that I would say is like some people say all AI agents are the same. And I would say absolutely not. If you look at the difference between, for example, like OpenClaw when it got released and Hermes when it got released. Hermes trajectory is just growing all the time. Why is that? It's because the way that it's been engineered with the self-learning loops, with the constant improvements, it's only getting better over time. Which means it's very different from any other tools out there. Also, some people say, I want a standalone app. I don't want to be able to customize it. But the thing is, if you do not customize it, you can't improve it because you can't mold it around you. And the problem is, if you are using AI agents standalone instead of building it into your own system, the biggest issue with that is you don't really get control in it. You can't build teams. You can't build systems. And if you're not building systems, you can't improve it, right? So if you look, for example, at ChatGPT, ChatGPT looks exactly the same today as it did two or three years ago. Why is that? It's because it's not really getting better or being molded to what you want. They've got one setup and they just keep with that. And so you want something really where if, for example, Minimax M3 drops and it's got a voice agent, you can plug that in today or in a couple of hours inside your system. And that's why I much prefer having my own custom setup like this. So thanks so much for watching. Which one do I personally prefer out of Odysseus and Hermes Agent? I'm going with Hermes Agent. I do think that it's great that all of these agents are coming out and they're open source and there's lots of cool new stuff coming out. That's always going to help in terms of innovation. If you want to get my full setup for the agent operating system, you can get that inside the AIPath for bottom. Just go to the classroom and then the agent OS, as you can see right here. You can grab the zip file, the full setup guide. And also we add new daily guides. We've actually got a full masterclass on how to use Odysseus. I do think it's a powerful tool. We've got a setup and instructions right there. And new daily tutorials, as you can see inside the community. You can ask questions, get help and support. There's always people online, so you can get help and support 24-7. You can also jump on weekly coaching calls. We have four weekly coaching calls where you get help and support in real time. And this is all inside the AIPath for bottom. Plus you personally connect me too. Thanks for watching. Cheers. Bye-bye.