How to Setup Hermes Agent in 1 Click (FREE!)

Today I'm going to show you how to set up Hermes in one single click. This is Hermes AI Agent, completely free and it takes about 20 seconds. Because most people think setting up an AI agent like Hermes is complicated. These technical terminal commands, GitHub repos, configuration files, it puts a lot of people off I know.

But it doesn't have to be like this. In this video I'm going to show you three different ways to get Hermes running in one click. A free cloud option, a free local option you can run on your own computer, and a hosted option if you want zero technical setup at all. No coding, no complicated installs, just Hermes AI Agent up and running fast so you can actually start using it.

Let's get into it. Alright so I'm going to show you the easiest fastest ways I know to do this. First thing you need to do is make sure you have Olama downloaded. You can get that for free at olama.com.

So make sure you've done that before you do this. And then once you've done that, you're going to go to the model section over inside olama.com. So you just go to models here, you select whichever model you want. If you're not sure what to use you can just go with deep seek.

That's designed for agentic tasks, it's pretty lightweight as well. And you can see here for example this is actually running through olama doing this method. So how does this work? Well all you need to do is you make sure you have olama downloaded, make sure you have it running, and then from here it's one single click as a setup.

So you copy this command right here, you go to your terminal, paste that in, hit proceed, wait for that to load, and then boom shakalaka my friend. You now have Hermes set up in one single click. So that's one of the easiest ways I know to do this. Now you can use cloud models.

Cloud models are free but they have token limits. So cloud models are free but they have token limits. Now if you wanted to set this up with a completely free model, well it really depends on your setup right. There's many different models as you can see on olama to run with Hermes.

Now I would recommend that if you are running this on a local model and you don't have a big setup, then olama is pretty good for this with Gemma 4. And Gemma 4 is a free local model right, free local model. You can get various sizes of them but they're super lightweight. Like look at that one, only 7 gigabytes.

That is very small for a local model. And again if you wanted to customize this to for example Gemma 4 with Hermes and olama, make sure you have olama running. We just go over here, we type that in, we hit proceed, and now this is going to launch with a local model right. So this is no longer a cloud model, this is a local model which means that we've got a free API running locally on my computer and then I run that with Hermes right and then I can just use it directly here.

So that's another option. So just to recap there, you can use the cloud model, that's like an instant setup. If you use a local model for example like Gemma 4 with Hermes, the biggest problem is like you may not have the best setup. Like I've got a Mac Studio so it runs pretty smoothly and then also it's going to take a while to download these and install them.

So it depends what your local setup is. If you have a powerful setup then you could go with this. If you don't have a powerful setup then you could go with one of the cloud models right. Now let's talk about another option which is you could use MaxHermes right.

So MaxHermes is basically a Hermes agent but it's hosted on cloud and you can install it in one single click right. It's pretty simple and easy. So the way that you do this, there's two options. You can run it locally you know if you've already got a minimax plan or what you can actually do is you can go to the minimax platform which is agent.minimax.io.

They don't actually make it that easy to access but you would go over here and the good thing about this is it's non-technical to set up. The bad thing about this is you know this is not a free method unlike what I've just shown you right. So just bear that in mind. Now if you wanted to set this up you just click on start now and then what this is going to do is wake up MaxHermes.

It's going to load the skills and then in literally like what 20 seconds that's just been set up and MaxHermes is now running directly inside the chat. There are some issues with running MaxHermes in the cloud but if you like non-technical stuff and you don't want to be in your terminal coding away this might be one of the best options right and you can just chat to it directly in here. One of the biggest problems is like you can't link this to your telegram or any other apps right. So it's just directly inside Minimax.

You can't link it to anywhere else. You can't upload files. I've tested out before it's not bad but it's not great I'll be honest with you but if you just want to get like a non-technical feel for this then you could try it. The other cool thing you could do here is you could test MaxClaw and MaxHermes.

So MaxClaw is OpenClaw another AI agent that's hosted in the cloud and then you've got MaxHermes. You can sort of compare them in the same platform and see which one you like right and the other cool thing about this is if you're using Minimax well Minimax can generate images and that sort of thing. So if you're using MaxHermes with Minimax all of the skills and the powers of Minimax for example images generating videos etc you could do inside MaxHermes straight out of the box right. You don't have to use separate APIs or anything like that.

So it's a really good like non-technical setup you just don't get the customization that you would with your terminal and so that's the biggest difference between them and again I would start with the Olama one. You know Olama with Hermes is pretty cool and the other cool thing about using Olama with Hermes is like you can just switch between models right. Something new comes out boom let's get that set up right here. This actually works with over 70 skills by default as well which is nice and then it runs with tons of different models right.

The recommended cloud models with this would be KimiK 2.5, GLM 5.1 cloud, Quen 3.5 cloud, Minimax M 2.7 cloud. Local models recommended with this are Gemma 4 and Quen 3.6. Now let me show you something else that's just come out recently as well. So if we go to Olama they just announced this today with the NVIDIA announcement which is the Nemetron 3 Nano Omni is available locally on Olama.

Now what's good about this is this is designed for agentic tasks but more importantly it's designed for like really efficient tasks right. So powering sub-agents this is the main benefit of Nemetron 3 Nano Omni right. So if you want something that can power your sub-agents and then maybe you have a main brain that's another good option as well but again it becomes more technical the more you set it up like that. So if you wanted to run Nemetron 3 Omni with Hermes what you would do is you would go down to Nemetron 3 as you can see right here scrolled and then you can run this with Omni as you can see so NVIDIA Nano Omni is available right now to start using inside there.

So that's another good option but bear in mind like that's uh it's quite a big model you know you're looking at like 28 gigs something like that but those are the the three options right. So you've got cloud, you got local and you got Max Hermes. Three good options for running and setting up Hermes in one single click. If you do want to go directly to the github page you can but I know that a lot of people struggle with this who are not used to using github and that sort of thing.

Honestly like if I was to set this up and I'm non-technical here's what I would do right. I would literally just copy that run Claude locally and then paste that in and just say set this up for me right and what Claude code will do is actually just set that up and install it for you. You can do the same with codex as well but if you're non-technical that's another option and again like it's just a one click setup where you hit enter and then it's going to start going off and and setting it up for you right. But yeah those are the three ways that I know to install and set up Hermes in one single click.

Pretty simple and easy as you can see. The other good thing as well like you've got plenty of options you can just try which one you want. If you're struggling to pick one I would go with Alarma. So thanks so much for watching.

If you want to get more trainings on Hermes, how to use it, how to set up, how to run AI agents like OpenClaude 2 you can get that all inside the AR Profit Boarding. Link in the comments description or just go to the arprofitboarding.com. Inside the community you can post questions, get help and support whenever you need it. Inside the calendar you can jump on four weekly coaching calls where you can ask questions about Hermes and AI agents.

You can share your screen, ask questions about your setup, meet other cool people doing the same sort of thing. Inside the map you can meet people in your local city who are also using AI agents like Hermes and OpenClaude. And then inside the classroom you can actually get all my best new trainings for AI. And I actually drop new daily trainings as you can see right here.

And one of the cool things about this is we have a full six hour course on OpenClaude and another two hour full course on Hermes right. So if you like this stuff you can find tons of training on Hermes which I think you'll like. Plus you can connect with me personally. So feel free to check that out.

Link in the comments description or go to the AIprofitboarding.com. Thanks for watching.