AI News Today
← All episodes
Episode 91 · July 23, 2026 · 09:35

Hermes just got 10x better (and FREE!)

Full transcript

There's been some huge announcements that make Hermes 100 times better. And I'm going to walk you through some of the latest Hermes agent updates and why this is so important. So number one, there's a new era of efficiency for your chat sessions in Hermes agent, which means that this can reduce the size on your disk by upwards of 78% to 78% smaller and an average 60% smaller to use, which means it's way faster to set up and way more optimized. Additionally, there are two, three models inside Hermes agent.

Number one is Laguna S 2.1. This is now free for two weeks on this portal. I'll show you how to set that up in a second. I'll show you some examples of what we've built with it.

And we also have HY3, which is your chat database just shrank by up to 78% using the new update from Hermes agent. And then additionally, you can now. Use HY3 and Laguna S 2.1 for free using Hermes agent, how do you set up? So what you can do is if you go to your manage section on your agent OS in grab mine link in the comments description, go to the model section of here, change the model, and then you can select news portal.

So news portal here, and you can use the free model. So you have 10 cent HY3 and also poolside Laguna S 2.1 for free. Directly with Hermes agent. Now, if you want to get the latest version, that's way faster and smaller to load, then you can actually update Hermes inside your manage section.

So go to manage inside agent OS, then scroll down, click on update Hermes. And from there, it can just automatically update to the latest version as you can see right here. So let's talk about the first one, your chat database shrinking up to 78%. Not very sexy, but it is big.

Basically Hermes stores every chat session in a local database and heavy users watch it balloon. The new optimization cuts it by 60% on average up to 78%. And if your database is under one gigabyte, the migration runs itself. So bigger ones get a prompt.

Now, why should you care? This means faster session loads. It means snappier history search and a lighter desk disc footprint on the machine that your agent lives on 24 seven. So before your chat was be a hundred percent after you're saving about 60%.

And you also got a bunch of one click free models that you can use with Hermes agent now too. So we have Laguna S2.1, HY3 and local from Olama. These will plug into your Hermes agent. And then you can plug that into your agent operating system to build and automate anything you want.

You might also say, okay, which model is the best? Is it Laguna? Is it HY3? Is it local?

Here's what I would recommend. So for us, when we were testing out, we've built out over 50 different things with each of these models. So when we were testing out Laguna, this is more of a free local model, but you can get it on cloud as well for free on news portal. So if we have a look at Laguna over here, you can score, you can see that it's scored pretty average when it came to our builds with Hermes agent.

Especially on local. I would actually say that out of all of those free models you can get access to, HY3 is your best option. It can create some pretty cool stuff and create some nice designs, et cetera. Let me show you a few examples.

So it can build like nice 3d games. It was pretty cool at building out these games like so as well. And it actually did a lot better just in general than anything else that we tested. So HY3 is your best option.

It's got a lot of features. It's got a lot of features. So for agent loops and coding, HY3 is performing the best. Hardest reasoning apparently is S2.1, but for my own tests, I would go with HY3 out of all of these.

Also, what you can do now, if you didn't already know is you can use cloud with news portal too. So this is cloud Hermes agent living in the cloud, and you can basically set it up in like 60 seconds. So you can sign in, just click through. It's literally just like click a couple of buttons.

And once you've done that, you can run Hermes cloud with Hermes agent. And from what I tested, it's even faster. So when you combine Hermes agent and the new updates in terms of smaller database, three models, and then use Hermes cloud as well, you know, you're absolutely going to crush. Also with the new dashboard updates, which I showed you before, like the manage section, for example, you can update in one single click and you get the models in pretty quickly.

So before, if you're looking at like a couple of months ago with Hermes, getting an agent meant running a terminal. A Python environment and evening you didn't get back. And then you'd be paying API rates to give it a good brain enough to master. And then also most people quit at stage one.

Like I've seen loads of people quit and then just completely cancel because they couldn't get it working. And they would just switch back to something, cloud, for example. Now you can install Hermes with a click, sign in to the portal, pick a frontier brain for free. And it takes like five minutes to go from zero to a working agent with HY3.

And also the other thing I would say here is like, if you're using an agent operating system, and this is what I'd recommend, really Hermes alone is an agent, but in the agent OS is an operation, right? So let me show you some examples of this. We pull up our agent OS over here. We can actually talk with our AI agent inside Hermes Apollo.

You can see the full transcripts of us talking over here. So let me show you some examples of this. So if we pull up our agent OS over here, we can actually talk with our AI agent inside Hermes Apollo. You can see the full transcripts of us talking over here.

What is built, et cetera. We can preview everything that's created. And this is just way more powerful than using agents alone. The other thing that you can do here is you can use Hermes Oracle.

So this actually every 24 hours pulls in the latest news from Twitter, marks it by what's trending, and then gives you links to the direct news update. Now, this is useful for staying up to date with the latest news, but then additionally, it's also awesome for creating social media content and publishing to WordPress as well. And then we have Hermes Astros, which can monitor your competitors. You can change the watch list over here and you can start creating content.

And we also have an outreach lead generation agent so that you can go inside the lead section with Hermes agent here. You can use Hunter API, type in the leads that you want, then you can draft the email campaign and then you can send emails with Hermes as well. And I think that's probably a much better way to use AI agents than what people are traditionally using. In addition, we have this pipeline with Hermes agent where if you have ideas, like lots of ideas for apps or websites or whatever you want to build, you can plug in an idea, capture it.

Then it goes through the human gate, then it gets implemented and shipped and found. So for example, if we go to the gallery over here, you can see all the cool stuff that we've actually built using this system. And these are all ready to preview and come back to whenever you want, which is pretty awesome. Now, you also might say, OK, doesn't running Hermes all day like cost a fortune in tokens?

But actually, because you've got that free local models that are available to plug in with OLAMA, and then you also have HY3 and you have the free agent from Laguna S 2.1. It is completely free to use for right now. Right. So some people think like setting up an AI agent is technical, but you've seen how easy it is to configure with Hermes and the dashboard.

And then other people say, well, free models are weak ones. But actually, if you check out GoldieBench, we've tested HY3, they perform better than some frontier models. It's not as good as like KimiK3 or, you know, Fable 5 or something like that, but it's a free brain you can plug in. And if you're running it on the cloud as well, it's going to be very fast, especially with the new setup where Hermes is now smaller.

And also some people say, well, I'll wait until, you know, things settle down and AI agents are fully solved by other things. But if you've been watching AI for the last five years, like I have, the thing that you'll notice is it never settles down. It just goes faster and faster. So you might as well implement it now before you fall behind from everyone else who's really implementing this.

Also, some people say, well, aren't AI agents like super technical? But if you look at our testimonials here from the AI Profit Boarding, we have over 203 pages of wins and testimonials and people learning and growing with AI. And these are all people who were non-technical before, but they learned how to use AI and they absolutely love it now. Right.

So if I can use it and I'm non-technical and these people are non-technical as well, then for sure we can all win and learn and grow together. And you don't need to be like a master in AI. You just need to get started. That's the main thing.

There's now no technical barrier to using this. So it's your move. The window is open. Walk through it.

One click for the Hermes agent, two free frontier models, a database that just got lighter and a community that wires every drop like this into a working system the same week it lands. So if you want to get our Hermes agent operating system, we have the installable agent OS zip file, Hermes pre-wired, Apollo voice agent inside there, the SEO content pipeline, agent Kanban, cruise, token minimization playbooks to reduce the amount of tokens costs you spend on AI, daily tutorials and four week coaching calls and 4,000 founders. Feel free to get that inside the agent operating system. Link in the comments description or go to the AIprofitboarding.com.

This is my AI automation community for helping you learn, grow, and save time with AI automation. If you want to get the agent OS from us, just go to the new daily update section over here, grab the agent OS. We've just updated it. You can get the zip file to install it.

Plus we add new guides based on what's actually useful and can help you grow. Inside the community, you can get help and support in real time, ask questions, et cetera. And then you can also jump on weekly coaching calls over here and share your screen. Also inside the classroom, you can get access to all my best training.

So if you're a complete beginner, you can go from beginner to expert over here. And if you want to meet people in your local area, we have a great way to network as you can see right here. So you can meet people in your local area and meet people near you who are using agents like Hermes to grow and learn the scale. So hope to see you inside there.

Cheers for watching. Bye.

More episodes

Browse all episodes →