Hermes Desktop + Ollama is Insane (FREE!)

**Julian Goldie** (0:00)
So today, we have a brand new update for Hermes Desktop, which allows you to use Ollama, and you can basically integrate your AI agents with using this one-click setup here. So what you do is you make sure you have Ollama downloaded, then you go to Ollama, launch Hermes Desktop, and from there, you can plug it into your Hermes Desktop app. And so from here, what you can do is you can run it for multi-agent workflows, so you can spawn parallel sub-agents with isolated contexts from the desktop. You can research several topics at once, run batches of stuff. Here's an example. And then this is also designed for using directly with Hermes, which makes it super easy. It can use all the same stuff. So what is also cool about this is you can also plug in Hermes agent to multiple channels as well. So if we go to the messaging section here, powered by Ollama, we can then connect this to Telegram or to Discord or Slack or whatever we want using this system, which is pretty cool.
And so Hermes agent is number one, easier to manage using Hermes Desktop. But number two, you can easily set this up. So how do you get this set up? Basically, the first thing you do is go to ollama.com and make sure you download this as you can see right here. So you can download it with one terminal command or you can click download Ollama. This is free to use. Once you've done that, you're then going to make sure you have it open like you can see here and if you've already used it before, make sure you've got it updated. Then once you've done that, you can just run this terminal command which is Ollama launch Hermes Desktop and this will launch your AI agents with Ollama. So it's pretty simple and easy to set up right there. Now, the benefit of using, you might be wondering, is that basically you can plug in, number one, local models and number two, free Cloud models to it. So with Ollama, they have many different models, for example, like Nemotron 3 Ultra. You've got, for example, Minimax-M3, and you can plug each of these models directly into Hermes Desktop. Now, you might also wonder, okay, why would you use Hermes Desktop?
It basically is better than using the terminal. It's not as good as an agent operating system. I'll compare these side by side so you can see the difference. Hermes agent is decent inside Hermes Desktop. It's much better than terminal, right? And the reason for that is because you can manage everything in one place. If you look at the terminal, the old way of doing this, if you go to the terminal here, I'll be typing Hermes. This is the old way of using Hermes, but look at that, it's just in the terminal. You can't manage anything, you can't see what you've built previously. It's pretty hard to see context and you can't preview anything that you build inside the terminal either. And so what we want to do instead is have some place to manage it. Now, Hermes Desktop is pretty easy to manage one version of Hermes, and it's a lot nicer than the terminal. So you can manage your skills, the messaging, the artifacts, you can see everything that you build, your images, your files, links, et cetera. You can also go over to your settings here and manage it here so you can change the model. You can set up the chat, you can change the appearance, and you can run this on local models because Ollama is now available for this.
Personally for me, I don't like local models that well, but what I do think is good for this is if I want to switch model quickly with Hermes Desktop, I can just switch over to Minimax or I can switch over Gemma 4 I could use Gemma 4 as a backup model, etc.
And that's the way that I would get the most out of it. So that's basically it. Now, if we look at this as well, I'm just going to change this over. I don't really like the setup there. Change that. There we go. There we go. Also, I'd recommend using dark mode inside Hermes Desktop. And that's basically how it works. So that's how to set up with Ollama, how to use free local models with it. If you're wondering, OK, which free local models would you recommend for using with Ollama? So if I was looking through the list here, I'd be like, OK, Qwen 3.6, pretty good. GLM 5.1, that's a pretty good model. Minimax-M3, obviously frontier level agentic model. It also depends on your setup as well. If you're just running on a super lightweight setup, then you can use something like Gemma 4, and you can plug this into Hermes agent as well. If you need something quick and light, then you can use Gemma 4