New Hermes Agent OS is INSANE!
AI News Today | Julian Goldie Podcast
October 6, 2026
New Hermes Agent OS is INSANE!
Speakers Julian Goldie
Julian Goldie (0:00)
So today, I want to show you exactly what we've built inside our agentic operating system for Hermes and break down all the cool stuff that we've built in directly. Now, the first thing that I want to show you is that you can actually use loads of free models with Hermes Agent. If you aren't aware of that already, basically what you can do here is you can have a look through the list and you can set up separate profiles with your Hermes Agent. So, for example, like you can use MIMO v2.6 Flash, which is free right now.
And also, there's a free API with open code that allows you to use Ling 3.1 Flash as well with your AI agents. Pretty cool. Now, next up, what we've actually done here is we built in bots, and this is a bot screen with Hermes Agent. Now, basically what this allows you to do is you can give each of your Hermes bots like their own separate computer screen, which is pretty cool. But then also, when you're building out with Hermes Agent, you can have separate profiles for each profile. So, for example, you see here the free API that I was talking about, link 3.1 flash free with open code. We can use that as a brain. Now, this is basically Hermes Agent's version of something like Grokbot or Dots, right? So, if you've seen Dots from ChatGT that just dropped, or you've seen, for example, Grokbot, you can basically give your AI agents a computer screen in the cloud, and these can run 24-7 without you using Hermes Agent bot screen as well, which is really cool. Now, over here, we have the Hermes Jarvis. So, this is Hermes Apollo, and we can basically speak to it. It will speak back to us, and then we can also see our full conversations of what we've had previously. So, it's basically like a voice agent. This is running on the Chat GPT real-time API, which is really good, super fast when you responded to it. And then also it can build for you in real-time as well. So, you can see all this stuff that is built and created in the background over here as well. Now, you could build whatever you want, you could even use a free open-source voice AI agent into this. But the whole point here is you can turn Hermes into a real-time kind of Java style AI agent just replying to you in the moment, using this system as we go along here. So, that's really cool as well. And then over here, we have Hermes Oracle.
Hermes Oracle is pulling in the latest news, and it's basically running 24-7, scanning what's just happened in the industry. You can see, for example, last consult is 10 hours ago. This is happening automatically in the background, and then it will actually show us the latest news. Now, if we want to have a look at the original post on that, we can go over here, which is super useful. But then also, if we want to draft SEO content, or you want to draft social media content, we can just click on Draft This, and it will draft it right there. Now, also, if we go back on previous day's news, we're like, okay, what happened Saturday? What happened Sunday, et cetera? We can go to our agentic operating system, and we can click between these days and switch between them. And the cool thing about all of this is you could easily switch between a different industry. You can connect to all your websites. You can see here all the content that we've created with this. And it's just super useful for creating content around trending topics, which is awesome for social media. It's awesome for SEO content. And it's all living inside this one single system. And you know how effortless it is just to switch the chat and then boss, and then Hermes, Apollo, and then Hermes Oracle. It's just like it's in one place. We don't have to switch to an app over here, and then an app over there, which is super messy.
Now, once we've done that, we can go to Hermes Muse. Hermes Muse is fantastic, because basically, it is your content assistant that's coming up with new ideas all the time. So based on what's just dropped, as you can see right here, so it's looking at our content, what's popped off, what's performing the best. It's analyzing our workflows, and then it's okay. Here's what's working right now, and here's what you need to create content about next, based on what's working. And it actually gives you an option to make the video based on this, or make the SEO article based on this, or even create an image for this as well. And you can literally just in one click go make the video, and then it goes over to our video agent. We can click write the script, and it will actually create a beautiful video, like you can see right here, right? So all of these videos you're watching are done with the AI agent that we've built in with Hermes, and it can basically put it all together. Super smooth workflow, which is beautiful.
8 more minutes of transcript below
Thousands of transcripts fetched by people building searchable podcast archives
Fetch the whole transcript
The demo key returns a sample episode in full, no card needed:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090Markdown with the speakers named, for your notes, your knowledge base, or anything that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Not what you expected? Email us within 14 days with 20 or fewer credits used and we refund the pack in full.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000793419292