Hermes Agent OS: FREE Local AI Agents + N8N! artwork

Hermes Agent OS: FREE Local AI Agents + N8N!

AI News Today | Julian Goldie Podcast

June 20, 2026

The video answers community questions about Hermes Agent OS, an agent operating system you can build and extend with workflows like video, SEO, music, and more.
Speakers: Julian Goldie
**Julian Goldie** (0:00)
So today we're going to be answering the latest questions on Hermes Agent OS. If you don't know what it is, basically, you can build your own agent operating system. And some of the questions inside the community around the one that I've built today, we're going to answer because I know if everyone has questions like those, then we can answer them publicly and help as many people as we can. And so, for example, you can see recently inside the system, I mean, we've built out all sorts of stuff, like a music agent, we've built out a video agent, SEO agent.
We even got the video agent to the point now where we can plug in a topic, it will go do the research, it will find relevant research to insert, and then it will edit it all together beautifully, as you can see right here. And it uses a combination of Minimax, HeyGen for the avatar, ElevenLabs for the voice, and Hyperframes to put it all together. It's absolutely wild. So today we're going to cover some of the best stuff that you can do with this. And this is just to inspire you and also just to help you.
If you're building your own Agent Operating Systems and if you're not building your own Agent Operating Systems, definitely recommend doing that because it's how you unlock the full power of Hermes itself and any other AI agent that we use. So let's get straight into this and see what we've got right here. So first question that we got from Khalid was, I have a Hermes Agent VPS from a hosting provider. How can I connect to Agent OS? So we give the zip file for Agent OS inside the App App for Boardroom. How do you connect to it for VPS? So we've actually got a really good tutorial from John who talks through exactly how to use it. So he deployed it with Hostinger, secured it with Cloudflare Tunnel, and then gave it Cloudflare Access. You can see the example Mission Control that used based on ours to create this agentic OS. So if you're trying to build your own, give it VPS access, you can do that. You can also use Tailscale as well, which is another decent alternative.
For me personally, I just host it locally because I think like that's a more secure way to do it. But if you do want to have a system where you can have your AI agents working, you know, from a VPS or working remotely from an agent operating system, this is how you can do it. So good question from Caled right there. Next question. So Will was asking, how do you plug the agent operating system into an existing dashboard? So let's say for example, you got an existing dashboard like this, and you're trying to use Hermes agent operating system to plug it in. How would you connect them, etc.
So the way that I would approach this, obviously there are two different systems and you're trying to merge them, which is a little bit complicated. But the way that you would do it is you explain to the agent, whichever agent built out your dashboard originally, hey, here's a new version of the dashboard, here's an old version. I just want to bring in some of the versions and some of the features from the new version inside the agentic OS into my old dashboard. And then just slowly build out one feature at a time. I wouldn't merge a whole thing at once, simply because if you do the whole thing at once, it's going to be messy, it's going to be complicated. Whereas if you simplify it down to just a few things or one thing a day, for example, one thing a week, then you can merge it slowly and you can build our agentic operating system into yours. The other option as well is, of course, that you could have sort of as we were talking about before with a VPS gateway, you could kind of have that linked to the client dashboard as well as another option. But I think that would be even more complicated. So I'd stick with version one. By the way, if you want to be able to ask me questions and also get our agent operating system, you can get that inside the AI Profit Boardroom. Link in the comments description or just go to the aiprofitboardroom.com. Daniel had a pretty cool result with a local AI setup. So basically he's been building out an image generator that works locally, which is pretty wild when you think about it. Using Ernie, which is a Chinese model from Baidu, so it can generate images locally. So if you're looking for like a local image generator, you can actually get this off of Hug and Face and then generate images locally, which is wild when you think about it. So one question we got here was about how to trigger an NA10 workflow from Claude. So let's say, for example, you've got NA10, you've got Claude.

11 more minutes of transcript below

Feed this to your agent

Try it now — copy, paste, done:

curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire.

Using your own key:

curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000773499475