AI News Today
← All episodes
Episode 55 · June 29, 2026 · 09:16

Hermes Agent 2.0 is INSANE!

Hermes Mixture of Agents 2.0: Beat Frontier Models with a Panel of AI Agents (Agent OS Demo + Benchmarks)

Julian demonstrates a new Hermes Mixture of Agents 2.0 setup that stacks multiple models as a panel of agents inside Hermes Agent, aggregating one prompt across several models into a stronger final output. He says he tested 42 builds with the same prompts and shows a leaderboard where systems like Fusion and Hermes Mixture of Agents rank above single frontier models, with side-by-side comparisons on Goldie Bench versus Claude Opus 4.8. He explains how the Agent OS simplifies running Mixture of Agents without terminal commands, saves outputs in a workspace, and includes tools like chat, talk mode, voice-controlled Hermes Jarvis, and Hermes Oracle. The key message is β€œdon’t chase the model, build the system,” noting you can mix cheaper, free, or local models to outperform top single models, and he points viewers to the AI Profit Boardroom for access, tutorials, and coaching.

00:00 Why This System Wins
01:03 How Mixture Works
02:16 Leaderboard Benchmarks
02:50 Opus Comparison Demo
04:01 Setup and Agent OS
04:39 Built In Agent Tools
05:23 System Over Models
06:50 More Builds and Costs
07:58 Get Agent OS Access
08:30 Community Proof and Wrap

Full transcript

Hermes Mixture of Agents 2.0 might be one of the most powerful systems that I've ever tested out, so this is a new system I've set up with the new Hermes Mixture of Agents release, so I'll explain exactly how it works, and I've tested it on 42 different builds, and it is absolutely mind-blowing in terms of what it can do and how it performs, and also how it performs versus everything else. So you can see some of the things that we've created right here with this setup, and basically what this does is it has multiple different models working together as a panel of agents that can build and automate anything that you want, and the point here is that you can create better outputs and higher levels of intelligence, higher than any frontier that we have currently, using a combination of agents working together instead of relying on waiting for these gated models like GPT 5.6 or for example MIPHOS to come out, and all of this stuff I've literally built today using Mixture of Experts, and on benchmarks versus everything else, which I'll show you in a second, this is outperforming pretty much everything. So how does this work? Well basically Mixture of Experts is a system where you stack multiple models together inside Hermes, and then you can be OPUS or GPT, and it's not with a bigger model but with a smarter system, and that's really what this is about.

It's about the models don't really matter, the system does. So what we've essentially done here is we've combined the newest Mixture of Agents model that came out from Noose Research, it's just dropped on Hermes agent yesterday, and we've plugged that into the agent operating system, where we can just chat with the panel, we can ask the panel anything, we can switch the APIs over here, and then this aggregates whatever we create, and then we can see everything that we've built inside our workspace over here, right? So if we ask it to do something like so, it will for example begin to run the panel, and then after that how it works essentially is that you have one prompt, and that will run through multiple different models, and it'll be aggregated into one better answer. Now the other power of this of course is that you're using Hermes agent, which is the most popular, powerful, open source, free agent in the world, which means that when you combine the agentic capabilities of something like Hermes with the power of something like Mixture of Agents, you're creating something that's really really powerful.

Now you might say okay that's great Julian, this stuff looks cool, but how does it perform against for example all the other frontier models that we have? Well right now I've got a leaderboard and I test again, I've tested this out on 42 different models, I've used exactly the same prompts across every single model that's out there that's actually useful, and the two top systems, and the keyword is systems here, at the top of the leaderboards are Fusion and Hermes Mixture of Agents. Cloud Open is actually down here, and if you're wondering why, well I'll show you that in a second. So I literally combined and created all this stuff, and you can test it out for yourself, see for yourself what you think on GoldieBench, but if we actually go to the compare tab here, and we compare Hermes Mixture of Agents versus for example Cloud Opus 4.8, Hermes Mixture of Agents is absolutely dominating, right?

The stuff that you can create looks way nicer than the stuff with Opus 4.8. Let me show you, for example like this looks way nicer than this kind of like buggy output that we got using the same technique. You can't even really control properly, and so like Opus 4.8 is still good, but Mixture of Agents basically makes it even better. It puts it into a better system where you can get more out of it, and also you're using the agentic power of Hermes alongside that, right?

So the cool thing about this is, for example, we've built out like these open world games, for example, like so, and if we compare this against something like this, it's just not quite as nice, right? Not quite as good. So overall, from what I've seen, have a look for yourself if you want to compare them side by side, but from what I'm seeing on GoldieBench, Hermes Mixture of Agents is absolutely destroying everything, and this is a trend that I've seen recently. It's like Fusion and Hermes Mixture of Agents, both systems, both panel-based models, and Fugu Ultra are all right at the top of the leaderboard because they just combine the best of all models and then have them working together, and that makes sense to me.

So if you're wondering how to use this, well basically you can go inside this terminal, and you can run the Mixture of Agents terminal commands like so. This is kind of technical, and that's why I actually put together instead something that I call the Hermes Agent OS, which you can see here. It's way simpler and easier to use, right? Because you can basically just go inside here, you can go to the Mixture tab, and then you can type in your prompt here, run the panel, and also the cool thing is, you don't need any terminal commands, you can just run this whenever you want, and additionally when you're using this as well, the cool thing is that all of your stuff just gets saved inside this workspace, so it's easy to preview, it's easy to come back to, and also you can combine that with the chat with Hermes Agents.

So what we actually have inside the chat is Mixture of Agents, so we can chat to it as well at any point. We have the talk mode where we can talk to our agents, we have Hermes Javis, which you can voice control, and it can use computer use, browser control, and we can preview anything that we've built with it, and then we have of course the Hermes Oracle, which you can pull in the latest news, and then we can draft content using it. We have the studio, but Mixture of Agents over here. The other cool thing that I like about having a system like this, is like when you're doing outreach for example, I can just build my own SaaS tool for getting leads, and building email campaigns, and finding the leads in like one single click using this system, and then we can then reach our campaigns, send out the emails, boom shakalaka, it's all in one, inside one place, right?

Way smoother and easier to use than if you're just inside the terminal or Hermes Desktop. So this is what we're finding so far, so a panel of experts beats one genius. If you've got one genius competing against five geniuses, typically you're going to get a better answer from a team of geniuses versus one person, and the other cool thing about this is, you know, whether you're using Fable 5 or GPC 5.6, which might come out soon, but might not, whether you're using for example Hermes Mixture of Agents, whether you're using Fusion, or for example, Fugu with Sukana Ultra, these are all similar models that work in the same way, which is panels of agents. Whatever you're doing, you can just plug into your system, right?

So for example, we've got Clause CLI, Fable 5 comes back, boom, we'll add it in. For example as well, we have a memory, and whatever happens, whatever model gets pulled down, this stays the same. Whatever happens with the system, whatever happens with the models, the system stays the same, we just improve every single day. It's like all this worrying about gatekeeping, and are these models going to come back, and which models are banned, which ones aren't, and which ones can't you get access to anymore?

You don't need to worry about anymore, right? All you need to do is focus on the system, and that's what I'd recommend for you. Don't chase a model, build the system, and that's exactly what we've done with the Agent OS for you. So if you want to get that, link in the comments description, or go to the AI Profit Boardroom to get access.

But yeah, it's super impressive from what I've seen so far. I know as well, the Hermes agent themselves have actually announced that they're going to be releasing a Hermes Bench, so we'll be able to see what their tests reveal as well, but I can imagine it's pretty similar to mine. I mean, we've even built our full operating system, as you can see right here, and we can open this up full screen, but you can see here, for example, you can build your own terminal. It's created like a Windows-style application here, where we've got the file, we've got the edit, the view, etc.

We've got all our terminals, and all our notes, and our apps, and everything else, and that's all ready to go, which is pretty cool. So anytime we need to build something now that's really amazing, I would recommend a system like this. And yeah, it just combines the best of both worlds. Bear in mind as well, you don't need to use super expensive models.

You could use free APIs, you could use local models, you could have cheaper models working together inside the system. The main point is, you know, several minds are typically better than one. And that is the whole system. And, you know, you can mix several models, you can beat the best single model, you don't need to wait for any frontier or gated models to come out.

And this goes beyond what we publicly have available, right? Like if you do this, you will get better outputs than if you have just Cloud Overs 4.8. Like that's literally, you know, and it makes sense, but when I've tested it myself, you will get better models and better outputs than the actual frontier models available right now. So it's pretty powerful stuff.

So if you want Hermes Agent with the panel built in, you know, the mixture of Agents, Fusion, Sakana, all running on the same idea, they all live inside Hermes Agent, inside the Agent operating system. And you get the dashboard around my whole business on the full Agent operating zip file, Hermes Agent, mixture of Experts, Fusion, Sakana, all wiled in. And these are all versions of the panel system where you have multiple models working together so that you can beat Opus 4.8 intelligence using our systems. You also get daily tutorials so you can stack models and also build great systems so it doesn't really matter what model comes out.

And you know, it's super powerful stuff. Also, you might be wondering like, you know, does this get results for everyone? So we have 3,800 members inside the AR Profit Boarding where you can get the Agent OS. And also we have 191 pages of testimonials and wins from people learning and growing with this stuff.

So I know like if, for example, these people can set up, you and I can set up too. And I'm non-technical, but I can still set this up. So obviously inside there, if you want to get the Agent OS, just go to the classroom and then go to new daily updates and you'll find the Agent OS over here. If you want to post questions inside the community, I actually answer them with video tutorials every single day, which is pretty cool.

And then inside the calendar, you can join more weekly coaching calls. Inside the map, you can meet people in your local area. And this is all available inside the AR Profit Boarding. Link in the description or just go to the arprofitboarding.com.

Thanks for watching.

More episodes

Browse all episodes →