Full Hermes Agent Setup Tutorial: Step-by-Step Walkthrough

Hey, I'm Caleb. In this video, I'll show you exactly how to set up your own Hermes agent step-by-step in the most beginner-friendly way possible. Hermes agent is a self-improving AI assistant that runs 24/7, connects to tools you already use like Telegram, Discord, and Slack, and actually learns new skills the more you use it. You can have it pull daily briefings from your Google Workspace, manage your GitHub repositories, monitor trending keywords, or whatever else you need it to do. The way it works is simple. You install a skill, set up an automated job around it, and your Hermes agent delivers results to you on a schedule without you having to prompt it first. And in this video, I'll teach you the easiest way to get all of that up and running even if you've never done anything like this before. Here's what we'll do next in this video. First, we'll deploy the Hermes agent on a VPS using a one-click template that handles the installation for you. Then we'll connect it to an AI model provider, set up Telegram so you can chat with your agent from your phone, and in the end, we'll make sure that everything is working properly. To get started, go to this link on screen right here or click the first link in the video description. That link will take you to the correct setup page and make sure you're getting the lowest pricing available on your VPS plan. And once you go to that link, you'll be brought to this page right here. Start by going over to the right-hand side. Here you can choose your VPS plan. By default, this will be set to KVM 2, and this is the plan that I recommend for running the Hermes agent. It's going to give you two virtual CPU cores, 8 gigs of RAM, 100 GB of NVMe disk space, and 8 TB of bandwidth. This will be plenty of resources to get you started. So, go down and click on deploy. From here, start by choosing your billing period. By default, this will be set to 24 months, which is a pretty long-term commitment. You can switch this from 24 months to 12 months and 1-month plans as well. I'd recommend going with the 12-month plan. This will still get you plenty of savings and a free domain for the first year. Scrolling down, you can choose if you want to toggle on daily auto backups, and you can also choose your server location. Hostinger will automatically choose the server location with the best latency for you. So, I'll leave this as the default location. Let's scroll up to the top. You can review your order here on the right, and don't forget to use the first link in the video description to get an additional discount here. With that done, go down and click on continue. From here, go ahead and enter your email address, create a password, and click on the register button to move on. Then on this screen, fill out your billing address and your payment information, and I'll meet you at the next step. From here, click on get started to move on. All right. And once you get to this screen right here, you'll need to enter your API key. For this video, I'll be going with the OpenRouter API key. I'm doing this because it gives you access to over 200 AI models with a single API key. So, instead of being locked into one of the other providers, with OpenRouter, you can switch models anytime with one command. This is also the most cost-flexible option, which matters when you have an agent running 24/7. So, to get your OpenRouter API key, go to this link right here. I'm going to go ahead and highlight it. Then I'll right-click on it, and I'll go to this link right here. And here, if this is your first time using OpenRouter, you'll need to sign up for an account. So, go down and click on sign up. Then go ahead and enter your email address, and create a password. Check this box right here, and click continue. And here it says it's going to send a verification link to your email address. So, go ahead and check the email address listed right here. You'll see an email that looks like this. Scroll down and click on sign up to OpenRouter. For this here, I'll click other, and continue. Then click create API key. Click create. For the name, we'll name this Hermes agent. And here you can choose a credit limit. If you leave this blank, it's going to be set to unlimited. So, if you want a cost guardrail and you're not looking to go over a certain amount, I would go ahead and enter your limit right here. In my case, for my agent, I'll set this to we'll say $50 for now. And then here you can choose when you want to reset your limit. You can choose between daily, weekly, or monthly. For now, I'm just going to leave this turned off. And then at the bottom right here, you can choose when you want this API key to expire. You'll see a few options right here, but again, for this video, I'll just go with no expiration. All right. With that done, go down and click on create. And right here, you're going to see your API key. Go ahead and click on this copy button right here, and make sure that you don't share this with anybody. I'm only showing you my keys throughout this video because afterwards, I plan on deleting everything. Since you've seen my API key here, that means it's now compromised. So, be careful with your keys and make sure you don't share them with anybody. So, now we have this key copied down, but before we switch back over to Hostinger, we need to make sure that we have our billing set up. If our API key is unable to load in new credits, that means nothing is going to work. So, let's close out of this. And then right here, you'll actually see your API key. You'll also see the usage, and then your settings regarding your limit. To get billing set up, go to the left-hand side here, then go down and click on credits. And then right here, you can add credits, or you can add a payment method to automatically top up your keys. In my case, I'll just click on add credits. And then from here, I'm going to fill out my billing address and my payment information. So, go ahead and do that and go through the next steps here, and whenever you're done, I'll meet you at the next step. All right. Now, as you can see here, I've now loaded credits into my account. So, that means after we go through the rest of the setup, our agent is actually going to be able to communicate with us and work properly. All right. So, now that you've added your credits and set up your API key properly, let's switch back over to Hostinger. All right. So, you should still have your API key copied down from earlier. If you do need to copy it again, just go back over to OpenRouter and find your API keys tab on the left. Now, let's go ahead and paste in our API key right here. And then at the bottom here, you'll see an option for a Telegram bot token. We'll get this Telegram bot token that way you can chat with your assistant through the Telegram desktop app, and more importantly, the Telegram mobile app. So, that way you'll be able to communicate with your assistant no matter where you are. So, in this case, I'll be using the Telegram desktop app. I'll go ahead and open that up on my computer now. And then at the top here, you'll want to search for @BotFather, and you'll be looking for this one here with the verified check mark. Go ahead and click on it. Then go down and click start. Go up and click on new bot. And then we'll give this bot a name. I'll name this one Medics Hermes assistant, and send it. And then we need to choose a username for the bot. And this username must end in the word bot. So, for example here, Medics Hermes assistant bot. Send that. And if that username is available, you'll get this message right here. At the bottom here, we're looking for this token. Go ahead and click on it, and that's going to copy it down. Switch back over to Hostinger, and paste in that bot token right here. With that done, go down and click on deploy. You may get this onboarding survey right here. Go ahead and scroll down and click skip. And as you can see here, our project is now being deployed. This process can take a few minutes to complete, so I'm going to fast-forward to whenever it's done. All right. So, now that our project is deployed, this is our VPS dashboard. You'll be able to see all of your server info and all of your different tabs and settings here on the left. But before we jump into the next step, I want to show you something real quick. Right here, you can see your Hermes agent listed as a Docker project. From here, let's click on manage. And right here, this is going to open up all of the details for our Hermes agent deployment. And then if you scroll down, you'll find your environment variables. Let's click into environment, and here you can see your OpenRouter API key and your Telegram bot token. And here are the values that we just entered during the setup. If you ever need to regenerate these or update them, you can edit them out right here. And if you need to add in a new environment variable later on, you can click on environment right here. All right. Now, let's scroll up to the top of the page, go to the right here, and click on cancel. And then right here, I want you to note down the last four letters that you see right here. We're going to need to use this in just a few moments. So, I'm going to copy this, and then I'm going to save it somewhere on my computer. All right. With that done, let's go to the top right and click on terminal. I'll be entering a few different commands into this terminal throughout the video. So, there's going to be a link down in the description that you can go to that will give you access to a Hermes agent setup guide. It's going to show you all of the different commands that I'll be using in this video and some other helpful commands for you later on. So, go ahead and open up that guide in a separate tab or on another monitor and continue following the video. Now, the first thing that we want to do here is navigate to our project directory. So, run this command. CD / docker / Hermes- agent- and then the last four letters that we just wrote down. In my case, that's GCZY. Go ahead and press enter. All right. Now, let's get inside the running container. From here, type docker compose exec -it Hermes- agent /bin /bash. Go ahead and run this command. And now we're inside the Hermes agent container. You may see warnings right here that say that the other API key variables are not set, and that's totally normal. Don't worry about this. Now, let's make sure everything is working properly. From here, type Hermes status and run that command. Okay, so now we can see our Hermes agent status here. And as for right now, everything is looking good. Right now, we can see that we have Telegram configured. And the next thing that we need to do here is select our model that we're going to be using. So, go ahead and type Hermes model and send it. And from here, you can choose the provider that you want to use. Since we set up OpenRouter a few minutes ago, we'll be going with OpenRouter. Press enter on your keyboard. And then from here, you can use the arrow keys on your keyboard to select the model you want to go with. By default, it'll be set to Claude Opus 4.6, which is super expensive. In my case, I'm going to go down and go with GPT 5.4 mini. But in your case, you can go through and look through these and choose whichever model you want to go with. Once you have your model selected, press enter on the keyboard. And that'll reconfigure your default model. And then to make sure that everything is running, the next command you want to enter is Hermes gateway start. Press enter. And in some cases, you may get this error right here. If this happens to you, go ahead and type Hermes gateway and send it. And then right here, it's telling us that the gateway is already up and running, which is good news. So, now the next thing that we need to do here is make sure that Telegram is working properly. So, that way we can actually talk to our Hermes agent. So, let's switch back over to Telegram. And then to open up a conversation with your Hermes agent, go ahead and click on this link right here. Then go down and click on start. And then you should get this message right here that contains a pairing code and a command. Go ahead and click on this command right here. And it's going to copy it down. Then switch back over to your browser terminal. Paste in the command right here. I'll do this using control, shift, and V. Then press enter. And then here, you can see that the user was approved. And that will be automatically recognized on our next message. Now, switch back over to Telegram. All right. Now, let's send another message here. I'll go ahead and say, "Hey, you're running on a hosting or VPS inside a Docker container. Can you check your environment and tell me what tools and skills you currently have available?" So, this is going to give your Hermes agent the context of where it's actually running, and it's going to let you know what you should do next. So, let's send this. And then here, you're going to see that it's typing, and you'll see the messages appear down here. And then here, we got a couple messages back. The first thing at the top here is regarding our home channel. You can click on this command right here to make this chat your home channel. Now, it says that cron jobs and cross-platform messages will be delivered here. And then scrolling back up, right here, you'll see your environment, the installed tools, and then the skills that are available. Right now, we have 73 skills installed across these categories. We have stuff ranging from creative, email, gaming, GitHub, productivity, research, social media, and much more. Now, my advice for you here is to look through whichever category sounds the most interesting for what you're trying to do, then ask your assistant how to set it up and what you need. And then work with it to create a recurring job. That's the whole workflow here. Find a skill, set it up, and then automate it. Let me show you what that looks like. I'm going to keep this simple here and set up a daily news briefing. This is something Hermes can do with its built-in web search, so we don't need any extra API keys or accounts for this. So, here, I'm going to send a message at the bottom that says, "Can you search the web for the top three AI and tech news stories today and give me a quick summary of each?" I'll send this. And then right here, it executed it perfectly. It gave me three of the top headlines today. So, just like that, it went out to the web, pulled in the latest news, and gave us a summary right here in Telegram. Now, what if we wanted this to happen automatically every single morning without us having to ask? That's where jobs come in. So, I'm going to send another message here at the bottom. This message says, "Can you set up a daily job that sends me a summary of the top three AI and tech news stories every morning at 9:00 a.m. Central Time?" So, let's go ahead and send that. And there it is. We now have an automated job that's going to send us a news briefing every morning at 9:00 a.m. right here in Telegram. We just told our assistant what we wanted, and it set it up. And that's really how you work with Hermes. You start with a skill or a task, you test it out, and then you turn it into a recurring job. The more you use it, the more skills it builds on its own, and the better it gets at helping you out. So, take some time, explore those skill categories I showed you a moment ago, and start building out your own workflows. All right. So, now before we move on, let's switch back over to Hostinger. And here, we'll end up back in the browser terminal. We've already done everything in the browser terminal that we need to do for the setup. And moving forward, most of the time, you'll be working with your agent directly in Telegram. But there are a few reasons you might come back to this terminal. For example, if you want to switch your AI model, you come back here and run the Hermes model command. And if you need to update Hermes to a newer version, you do that here, too. Or if something ever stops working and you need to check on things, you can run a Hermes status or Hermes doctor to see what's going on. At the bottom of the Hermes setup guide that's linked in the description, you'll find a list of different helpful commands that you can use in the browser terminal. So, feel free to save that guide for later, just in case you need to use those commands in the future. With that said, let's switch back over to the Hostinger dashboard. And let's take a look at the left side over here. From here, you can click into your overview tab. And this will show you more information about your VPS. And then in Docker Manager, that's where we just were. If you want to deploy other projects, you can do that right here. You also have your VPS settings, your operating system and control panel. You also have backups and monitoring. Click into this here. And here, you can manage your backup schedule, and you can also create snapshots. I would recommend doing this anytime you're about to make a major change to your VPS. Here, you also have your security settings and your DNS manager. And if you ever run into any issues with your VPS, you can go to the top right and contact Hostinger here. You now have your own Hermes agent up and running. It's fully ready to start installing skills and creating automated jobs. And if you haven't set up your VPS yet, don't forget to go to this link on screen right here or click the first link in the video description to get the lowest pricing available. Thanks for watching this video. If it helped you out, leave a like on it and subscribe for future tutorials. And if you run into any problems, just drop a comment down below, and I'll do my best to help you out. With that said, I'll see you in the next one.