Why You Should Install Hermes on Windows Right Now for FREE

We have yet another agent in the market, which is Hermes agent, which was developed by Nous Research, and it is mind-blowing. This is one of a kind agent that actually learns by itself in a loop. And in this video, I'm going to show you how you can install this on a Windows PC because this is only available for Mac, Linux, and Termux for Android device. So, what we're going to be doing is we're going to go through the GitHub repo. We're not going to make things very complicated. I'm going to show you the easiest way to set this up locally on a computer. And also, I'm going to show you how you can run this with local models if you want to, and also Ollama's cloud model. Everything that we're going to do in this video is going to be completely free. So, stick till the end of the video so that you know how you can set up this amazing agent, which is just mind-blowing. So, without further chatter, let's dive right in the video and start exploring Hermes agent. Hi, and welcome back to SkillCurb. This is your host, Shamraiz, and we're finally getting started with this video. So, we're here at Nous Research Hermes agent repo. And if we scroll down, let's talk a little about Hermes agent. So, it is a self-improving AI agent built by Nous Research. What it means by self-improving is that it's the only agent with a built-in learning loop. It's going to repeat, learn from its experience, and improve during use. And you can pretty much run this locally on a computer. There are a couple of ways of how you can access this, whether you want to set this up locally or you want to use third-party platforms like Minimax and Hugging Face. But in this video, we're going to show you the easiest way to install this and also to

use. So, for that, the very first thing that you're going to want to do if you're on a Windows PC is that you need to install WSL, which is actually Linux for Windows. And you just have to click here or open this up in a new tab, and this should take you to this page here where you can just go ahead and copy this, open up your terminal, pretty easy, and just paste that in. And it should install WSL. Now, I already have this installed and once you have installed this, you're going to see this Ubuntu right over here. So, here is where we're going to set up everything. We're going to run Ollama and Hermes agent inside this environment over on a Windows PC. So, once you have this

installed, you just go back to this Git repo and you just copy this command right over here. Now, this is a quick install and it's going to install Hermes agent on your computer. It's not going to take much time depending on the speed of your internet. So, you just paste in the command and hit enter and it's just going to go ahead and install everything that it needs, dependencies and stuff. So, let's go ahead and do that and I have to give my root password. And that's it. There you go. It starts downloading stuff and installing it. Once this is installed, it's going to install everything. It's going to check whether you have Python or not, whether you have Git or not, Node, and even packages like FFmpeg and Ripgrep. And once everything is installed, you can run this on your computer. And you don't have to do technical stuff. This simple command is going to do everything for you. Now, there you go. We have Hermes installed and now you can go ahead and configure it. But this is just one way of installing Hermes. We have multiple ways of doing that and I have a better way where you don't have to even configure the provider model and my

sitting stuff. And for that, you have to go to Ollama. So, all you have to do is head to ollama. com. You have to install Ollama for your Linux. So, for that, you have to go to Linux, copy this command right over here, and paste that inside your Ubuntu terminal. I already have Ollama on this user on WSL. So, what I'm going to be doing is I'm going to skip that step and I'm going to go right into the models. Now, here you have to decide which model you want to run it with. So, DeepSeek-V4-Flash is it relatively new model and you have the cloud version of it, which is really helpful if you don't have enough hardware capacity to run local models on your computer. So, what I'm going to be doing is I'm going to scroll down and here I'm just going to go ahead and say, "Hey, Hermes agent. " let's copy this command right over here. " It's going to launch Ollama and Hermes with the model deep seek before flash cloud. Now, the cloud models might have a bit of rate limiting, but it is the easiest way to set up a free model because otherwise you will need to have a very good hardware to run these models locally. So, what I'm going to be doing is going back to my Ubuntu terminal, pasting in that command that I just copied, and hitting enter. And there you go. It's going to ask us, "This will modify Hermes agent configuration. " And I'm just going to go ahead and say, "Hey, yes. Let's go ahead and do that. " Now, it's going to ask us whether we want it to message on Telegram, Discord, Slack, and more. So, here you have to choose whether you want to add a messaging app with it or not. For now, I'm just going to skip these steps because the purpose of this video is to show you how you can set this up locally on your computer. So, I'm just going to go ahead and say, "Set up later. " And that's it. Hermes is working on your computer right over here. So, let me go ahead and expand this a little bit so we have a better view. So, there you go. We can see that Hermes is working on a computer within just a simple command that we copied and pasted in. It is not that technical. And the best part about this is you don't have to have a very good hardware specification for this because everything the model is on the cloud and that too for free. Although there is a certain rate limiting with that and to see that you just have to go to your profile and here you can see the cloud usage. I haven't used a single percent of this free cloud usage and it resets in 2 hours and one is going to reset in 3 days, which is really good. We can even go ahead and generate keys to log into our Ollama account. Now, this is with the cloud model. Now, what

if you want to go with the local model that is hosted on your computer? For that, I would recommend that you go with something like Gemma by Meta because it is relatively smaller model. If you scroll down, you can see that the smallest model of Gemma 4 2 billion parameters requires 7. 2 GB of space. So, it is relatively easy to set up. So, all you have to do is just copy the same command but add a colon and e2b at the end of it and it should download and run this model locally on your computer. Now, this was how you're going to set this up locally, but we also have a paid

alternative to it. And for that, you have to go to agent. minimax. io/maxhermes and here you can actually run this inside your browser, but it will not be that helpful as it is when it's going to run on your computer because it is an agent and agents ought to run on your computer rather than just browsers and sandboxes. So, yeah, that is a downside of running this over at the browser, but it is the easiest way. So, I hope this

video was helpful for you to understand how you can actually set this up locally on a computer and you don't have to be very technical to run this. I'm going to be continuing this series where I'm going to make video on how you can actually utilize this in daily life applications and also setting up different skills and tools with Hermes. With that said, I want to wrap this video up. If you found this video insightful, hit that like button. Share your thoughts in the comments below. Ring that notification bell to never miss out on the daily updates. Thanks for watching and we'll see you in the next video. Till then, stay curious and keep exploring.