# Master Hermes Agent in 20 Minutes (Beginner Tutorial)

Channel: Metics Media
Video: https://www.youtube.com/watch?v=q5RagIqBtjc
Duration: 21 min
Language: English - Default
Words: 4406
Transcript page: https://viewrankai.com/tools/youtube-transcript/q5RagIqBtjc

---

[0:00] - Let me show you how to master Hermes agent (graphic whooshing) in 20 minutes, (graphic clicking) even if you're a complete beginner. (transition whooshing) When we're done, your agent will be running (graphic chiming) on its own. (graphic whooshing) It will check the things (graphic clacking) you care about and text you (graphic whooshing) when something's new, (graphic beeping) and it will remember exactly how you like (graphic whooshing) things done. (graphic chiming)

[0:16] We'll start from zero. (transition whooshing) And there's no code (graphic clacking) or terminal required. (graphic trilling) If you can use a browser (graphic whooshing) and a chat app, (graphic beeping) you can do this. (transition whooshing) I'm Matt, and I use Hermes every day. My agent has over 20 scheduled jobs (graphic beeping) from watching flight prices to planning trips. (graphic beeping) Hundreds of thousands (graphic beeping) of people have watched my Hermes videos (graphic chiming) here on YouTube to set up their own agents. (graphic chiming) So I know which parts matter. (transition whooshing) (transition whooshing) A few core parts do most (graphic clicking) of the work, and that's all we'll set up. (graphic chiming)

[0:41] (graphic whooshing) Hermes itself is free. (graphic beeping) You'll only pay for the server it lives on and the model it uses. (transition whooshing) We'll do it in five steps and each step answers (graphic whooshing) one question. (graphic beeping) (graphic whooshing) Should your agent live on your own computer (graphic beeping) or somewhere else? (graphic whooshing) Which model should it use (graphic beeping) so it's smart (graphic beeping) but still cheap? (graphic whooshing) How do you message it from your phone? (graphic chiming) What should its first job be? (graphic chiming) (graphic whooshing) And how do you teach it something once (graphic beeping) so it remembers it in every new chat? (graphic chiming)

[1:04] (transition whooshing) Every step is timestamped below, so you can jump to any step later. Let's start with the first question, where your agent should live. (transition whooshing) (graphic beeping) Your agent needs a machine to live on and that machine has to be three things. (graphic whooshing) It has to be awake. (graphic beeping) Your scheduled jobs, (graphics popping) the watching and the messages it sends you all depend on the machine being on at 3:00 in the morning (graphic popping)

[1:27] and the laptop in a bag isn't on. It has to be separate (graphic whooshing) from your things. An agent runs commands, instals software, writes files, deletes files. While you're learning, you want all of that happening somewhere with nothing of yours on it. No personal photos, (graphic beeping) no passwords, no sensitive work documents and no browser logged into your bank. Think of it as a practise workshop. (graphic clicking) You're going to make a mess in it, (graphic clicking)

[1:51] which is what it's for. And if you ever break it badly, you delete the whole thing and start again in 10 minutes. (graphic popping) And it has to be... (graphic beeping) reachable. So, your phone, (graphic beeping) your laptop and your tablet are all doors into the same agent. That machine is a VPS, a virtual private server. It's a computer in a data centre (graphic popping) that stays on all the time and that only (graphic whooshing)

[2:10] you can log into. And the smallest one costs just a few dollars a month. (graphic beeping) You can instal Hermes on your own computer instead, (graphic whooshing) but then it only works while that computer is awake, and it's running commands and deleting files right next to everything you own. (graphic chiming) So, for your first agent, rent the server. (graphic beeping) Now you can rent a server from plenty of companies (graphic beeping) and on almost all of them you'd be installing Hermes yourself from a terminal, (graphic beeping)

[2:34] which is the text window you may have seen programmers use. That's the part I want to skip. And it's the reason (graphic whooshing) we're using Hostinger. (graphic beeping) They have a one-click Hermes template that does (graphic beeping) the setup a beginner (graphic clicking) shouldn't have to touch. It instals Hermes, puts it behind a secure web address, (graphic beeping) gives you a login page (graphic beeping) and adds backups,

[2:52] one-click updates, and a restart button. It's also one of the cheapest (graphic popping) ways to do it. Throughout this tutorial, (transition whooshing) you'll see how everything looks while I'm recording, but software like this gets updated all the time. (graphic whooshing) So a button might be somewhere else. (graphic whooshing) Things might have different labels and there might even be new features (graphic beeping)

[3:09] by the time you watch this. (transition whooshing) If something seems different, don't panic. Follow the general idea rather than the exact visuals. (graphic beeping) There are just two things that cost money today. The server, which is just (graphic whooshing) a few dollars a month (graphic beeping) and a model account in a few minutes, (graphic popping) which costs about the same (graphic beeping) as a streaming service. (graphic whooshing) So let's start by grabbing our Hostinger VPS. (graphic beeping) Use the link on screen or the first link in the description below. (graphic chiming) It stacks an extra 10% discount on top

[3:34] of any sale Hostinger is already running. So using that link is the absolute cheapest way to get started. (transition whooshing) When you click on that link, you'll land on this page here. And if you click the Choose plan button, it'll scroll you down to see the various plans that are available. Here you can see that our coupon has already been applied, so all the plan prices

[3:50] that are listed are the prices you'll really pay. I recommend taking the KVM1 plan. It's the smallest plan and it runs one agent comfortably. And if you ever outgrow it, you can simply upgrade later without reinstalling anything. So go ahead and click Choose plan. You'll land on the cart, and here you'll need to make a few selections.

[4:09] The first one is your registration period. Longer terms are cheaper per month, but the discount needs at least 12 months. So 12 is the shortest I'd pick. There's a 30-day money back guarantee, whichever you choose. Then there's a box that's already ticked for Ready to use AI. Go ahead and untick it. It signs you up to a different AI service you don't need,

[4:31] and we're bringing our own in a few minutes. Leave the rest of the add-ons alone and then check the discount is showing on this page and then click Continue. On the next page, you'll need to register your account. Go ahead and register with Google, GitHub, or email address. I'll use an email address. Create a password, and then enter a phone number

[4:51] if you'd like, but that's optional. So I'll go ahead and click Register. Then on the next page, enter your billing address, and your payment details to complete the transaction. I'll do this offscreen and meet you on the next page. After payment, you'll get this confirmation and then Hostinger should route you straight into the Hermes setup flow with a form

[5:08] that gives you an admin username and a password. Here you can keep the username as Hermes or change the admin username to whatever you want, just make sure you remember it. And then go ahead and click the eye to toggle on to see the admin password. Go ahead and copy this and then save it somewhere safe, like a password manager. Don't save this in text notepad

[5:29] or anywhere insecure that somebody else could find it. This is how you're going to access your agent and you want to make sure it's locked down. (graphic whooshing) Once you've got that saved, go ahead and click Deploy. (graphic whooshing) You'll see this loading page for a few moments (graphic clicking) and then you'll be routed into Hostinger's dashboard. You might be presented with this survey,

[5:46] you can fill it out or click Skip. (graphic whooshing) And here you can see at the bottom, at the right, that the application is still being deployed. If you see this, wait a few minutes until this Hermes agent application changes to a green check mark status and says Running. Here you can see I got the application deployed confirmation,

[6:06] so we are all ready to go. Once you've got it all set up, you can manage your Docker application that holds Hermes here in the Applications section of Docker Manager. We have two things installed here right now, the actual Hermes agent and traffic, which secures your connection to the server. (graphic whooshing) (graphic chiming) Setting up Hermes used to mean a terminal and a long list of typed commands. (transition whooshing)

[6:27] On this route, you never touch a terminal. Your agent is already reachable through a browser and you log in just like any other website. On the Docker Manager page, go to your Hermes agent, and under the access column, click the Open link. This is the login page for your Hermes dashboard. Go ahead and save this URL in your bookmark

[6:45] so you can access it later. Once you've done that, then go ahead and sign in with the username and password that you saved earlier. Welcome to your agent's control room. Let me give you a quick orientation before we change anything. On the left side, we have the nav menu. Sessions is every conversation your agent has ever had

[7:03] on any device, and they all share one memory. Models is where you pick the AI that does the thinking, and that's the first thing we fix because right now nothing is chosen. cron is the schedule, the page that lets it work while you're asleep. In the top of the nav section, if you click Chat,

[7:20] it'll load a retro terminal style chat. And here, if you try to type something like, in my case, I'll say hello, you notice that nothing really happens. In fact, we get this error that says no inference provider configured. On the upper right too, you'll see there's an error. So your agent is installed and running,

[7:38] but it can't think yet. It needs a model provider, which is the account that supplies its intelligence. And the gateway on the left side is the part that connects it to the outside world. It carries messages to and from your phone later. Right now, it has nothing to connect to. We'll fix the model first, then we'll connect your phone. (graphic whooshing) (graphic beeping) A model is the AI that does the thinking, the brain your agent borrows, (transition whooshing)

[8:02] and it's the same kind of AI that runs ChatGPT and Claude. Hermes doesn't come with one, so you give it an account that supplies one. We're using Nous Portal, made by the same people who make Hermes. Nous Portal is built into Hermes, so you simply connect it by logging in with no access codes to copy anywhere. One account gets you access to more than 200 models from all the major AI companies, and it supplies the tools your agent works with, web search,

[8:28] reading, webpages, image generation, browsing, and speech. $20 a month buys you $22 of credits. Sign up with a second link in the description below. That link takes $15 off your first paid month, so month one only costs you $5 and you still get $22 of credits, which covers everything in this video and weeks after it. That link will take you to this page here where you can see the invitation banner,

[8:54] and you'll also see the deal I just mentioned. Go ahead and click the CLAIM YOUR INVTE link at the bottom. You'll get this pop-up saying, "Welcome to Nous Portal." Go ahead and create an account with Google, your email, GitHub, Discord, or one of the other options. I'll use my email again. You may need to enter a six-digit code from your email.

[9:16] Go ahead and open your inbox and grab that and paste it in. You'll get a success message, and then you'll be routed to the checkout page, and you can see that the discount has already been applied to your order. Go ahead and check out. I'll do this off screen and meet you on the next page. After checkout, you'll land on this confirmation page and you'll see on the left side

[9:34] that your account has been loaded with $22 of credits. Back in the Hermes browser dashboard, on the left side nav, scroll down and click into the KEYS page. Here, the first option is Nous Portal. Go ahead and click the LOGIN button to the right. Here, this will open a window, and it'll say, "ALLOW HERMES AGENT TO USE YOUR PLUS PLAN."

[9:54] You can click the CONNECT button to activate it. You'll get a confirmation saying it's connected and you can close the page and return to the Hermes agent. So we'll go ahead and close this tab, and you can see back on the KEYS page that Nous Portal is already connected. Now let's pick a model. On the left side,

[10:09] scroll back up and select the MODELS page. (graphic whooshing) Here, click Change next to MAIN MODEL, and here we get a whole list of models offered by Nous Portal. I recommend to start with a fast and cheap model because you'll send a lot of messages while you're learning. DeepSeek Flash is perfect for this. Go ahead and search for DeepSeek

[10:28] or scroll down and find it in the list. Here you'll see a few options. There's deepseek-v4-pro, DeepSeek V4 pro 0813, and deepseek-v4-flash-0731. These are the models at the time I'm recording. We want the flash model, and I recommend just going with the newest version of whatever it is by the time you're watching this.

[10:49] It could be deepseek V4.1 or even five, six, seven. Don't pay too much attention to the number. The one we want is deepseek-flash. Now, the reason we're using DeepSeek is because it's good at using tools and a message with it costs a fraction of a cent. So we'll go ahead and click that, and then click Switch at the bottom. It gives you a dialogue

[11:09] asking if it's okay to switch the model. We'll click Reload. Let's go ahead back to our CHAT page. We'll click that in the upper left, and then here in the upper right, you can see that we now have deepseek selected as our model. Let's go ahead and type a message in the chat here.

[11:24] I'll say, "Hello," and hit Return on my keyboard to send it. And we get a response. It says, "Hello, what can I help you with?" Two minutes ago, this agent couldn't answer anything at all. Now we can ask it anything. So let's ask what tools it came with. I'll say, "What tools do you have?" (graphic whooshing)

[11:44] And it comes back with a list. It has a built-in browser. It can run terminal commands, work with files, do code execution, search the web, delegate to sub-agents, use memory, schedule things, and a whole bunch of other miscellaneous tools. Your agent can think now. Next, let's give it a way to reach you. (graphic whooshing) (graphic beeping) Right now, it lives in a browser tab, but we're going to give it its own Telegram account so it can reach you when you're nowhere (transition whooshing)

[12:10] near this dashboard. We're using Telegram because it's the easiest one to set up. It just takes one quick scan of a QR code with no codes to copy anywhere, and it's a great messaging app to use day-to-day. You get fast replies and you can send files, voice notes, and photos all in one thread. Hermes supports more than 20 other platforms too, including Discord, Slack, and WhatsApp,

[12:32] and you can add one of those later from the same page. Before following along, get your phone out now, instal Telegram if you don't have it, and keep it nearby. I put a link in the description below that takes you straight to the Telegram download for your phone or desktop so you don't have to go looking for it. Back in your Hermes web dashboard, on the left side,

[12:49] click CHANNELS in the menu. Then find the Telegram channel. Here you can see it's disabled. Go ahead and click the toggle at the upper right to turn it on. You'll need to click the RESTART button for that change to take effect, so go ahead and click that, and you'll get a gateway restarting pop-up. You'll get a message saying the gateway is not running, and then this will take a few minutes

[13:08] for the gateway to turn back on. If you don't see it turned on after a few minutes, I recommend going ahead and clicking refresh in your browser. And here you can see now that the gateway is running, but there's no bot token configured for Telegram and it is turned on. So let's go ahead and click

[13:24] CREATE WITH QR to connect the Telegram bot. All right, now grab your phone and get your camera app up. Then go ahead and scan the QR code and open the link. Here you'll be taken to a conversation with the Nous-hosted Hermes bot. Click Create bot and then Create.

[13:41] That'll take you into a conversation with your Hermes agent, but the bot's not fully connected yet, so go ahead and hit Back on Telegram and select that Nous-hosted Hermes bot chat from the list, or if it's not there like it's not in my case, go ahead and scan that QR code again to pull it up. And that'll take you back to the conversation

[14:00] with the Nous-hosted Hermes bot. And here you can see that there is a message that says Connect this bot to your Hermes setup. Go ahead and click the Connect this bot button. And then you'll see at the same moment that you get a bot connect notification in Telegram, your bot appears in the web dashboard as well.

[14:19] Here's the bot name, and then here's the allowed user. This is your Telegram ID. To lock this in, go ahead and click SAVE AND RESTART. And this can take a few minutes just like that first restart change. So give it a few minutes to restart, and if after a while it doesn't flip back to showing it that everything is running, go ahead and click refresh in your browser, and then you'll see that Telegram

[14:37] is connected and your gateway is running. Now, in your Telegram app, you can go ahead and tap on the username for your bot, that's the @hermes_ and series of numbers and letters. That takes you back into the conversation with your bot, so go ahead and click Start. And the start command doesn't actually start the conversation, you have to send a message.

[14:54] So let's test that out. We'll say, "Hello, can you hear me?"

[15:04] And you can see that the Hermes agent is typing a message. You also get a message saying that there's no home channel set for Telegram. The home channel is where Hermes delivers the Cron job results and cross-platform messages. So go ahead and simply tap the /sethome command, and then that sets Telegram to be your home channel. Now, anytime a Cron job runs and it needs to send you a notification,

[15:25] Telegram is where it will send it. And you can see the message that came through here. It says, "Yes, I can hear you loud and clear. What can I help you with, Matt?" Let's cover safety. This flow just put your Telegram account on the allow list, so if anyone else finds your bot and tries to message it, they get nothing back. And Telegram bot chats aren't end-to-end encrypted,

[15:42] so don't send it passwords or banking details. For everything we do today though, it's fine. Now, if your bot ever goes quiet, there are three things to check in this order. First, check your credit and your rate limits with your model provider because that's the usual cause. And Hermes is good about telling you when it happens,

[16:01] so look at your last message. Second, the gateway. Here you can see my gateway status is running, but check this if you're having any issues and click Restart if you see anything strange. That can help to fix a silent bot almost every time. And then third, the logs. You can find the logs in the left sidebar

[16:19] near the top of the list. Here are all the different logs and you can filter through by type, all debug-related logs, info, warning, and errors. Logs is your agent talking about itself. You don't need to read every line, but just filter for errors when something seems like it's going wrong. And if none of these three steps fix it, restart the whole application

[16:39] from Hostinger's Docker manager. Click the three dots next to your application and then restart. Your agent has a home, a model, and a phone line. Now, let's give it (graphic whooshing) its first job. (graphic beeping) A great first job is a watcher. (graphic whooshing) A watcher checks something on a schedule and it only messages you when something changes.

[16:59] I'm going to tell my agent what I care about once. It'll write its own skill for checking, schedule itself, and then from then on, my phone only buzzes when something's actually new. A skill is a set of step-by-step notes your agent writes for itself so it can do the same job again. I'm typing this in the Hermes desktop app. It's connected to the same agent

[17:20] so you can send the exact same message from Telegram. In a new session, let's say something like this. Watch Barcelona to London flight price trends for me. Build yourself a reusable skill for the check, keep track of what you've already shown me, schedule it every few hours, and message me on Telegram only when there's something new.

[17:39] So this job was a cool one to watch. This one actually took about 30 to 45 minutes, somewhere in there. I actually stepped away and came back because it was taking a while. So the agent went onto the live internet, figured out the best way to do this job, built the machinery, built a skill, put it on a schedule, and also set up some memory so it can keep track

[18:00] of what it's already shown me. And then here after all that work is its first response, basically saying that it'll message on Telegram only when something changes. If we go to the Scheduled jobs... (graphic whooshing) we can see now we have this Barcelona-London flight price watch. So it'll run this script every six hours,

[18:20] fetching the latest prices. And there you can see unprompted after something changed, this is what it looks like when the flight watch Cron job finds something new. I described an outcome once and now it comes to me. My own agent runs more than 20 of these. One checks my bookkeeping every Monday, one tracks birthdays and starts researching gift ideas

[18:41] while there's time to order. One works on a trip I'm planning twice a day, getting quotes and coming back with the best option, and one follows up on a negotiation so I don't have to remember to do it. Flights are just my example. You can point your watcher at a price, news about a topic you follow, or even tomorrow's weather.

[18:59] Some websites block agents. If that happens, ask your agent to find another source. (graphic whooshing) (graphic beeping) You've probably had this experience with AI. You correct it, it fixes that one reply, (transition whooshing) and then the next session, it's already forgotten and you're correcting it again. Watch what happens when you correct Hermes. As an example of something simple that I might correct Hermes on,

[19:19] I'll have it write a short social media post. I'll say, "Write a short post about studio lighting for complete beginners." And here you can see it comes back with headings, bullets, and it's quite wordy overall. It's not as short as I'd like, so let's give it a correction. I'll say, "Too wordy. I prefer short, punchy sentences, three paragraphs max,

[19:40] no headings or bullets, save that as a preference." You can see it saved that to memory. It said it was saved and then came back with a much better structure. I told it plainly the way you would tell a new hire as you're training them, and then it wrote that down in its memory. I didn't have to go find a settings page

[19:59] or edit anything, I just told it. But now, watch what happens when we go to a brand new session. Now I'll say, "Write me a short post about roasting coffee." And there's the exact same structure again. That was a brand new session with nothing carried over and it's still in the shape I asked

[20:18] for once in a completely different session. Any chat bot can hold a preference inside of one conversation because it has the context of that one conversation it reads through when it responds. This one, on the other hand, holds it across every conversation on every device from now on. (graphic whooshing) (graphic beeping) So what does all of this cost? The server is a fixed (graphic whooshing)

[20:39] price every month. The model is the part that changes because you pay a tiny amount for every message. You can see exactly what you've spent on the USAGE page in Nous Portal. On the first day I set up my agent, the model cost me a little over eight cents. Your agent is now working for you 24 hours a day. To connect it to the apps you use every day

[20:59] and give it a team, watch my full Hermes agent guide next. It's on screen now. And if you still need a server, use the link on screen or the first link in the description. It gets you an extra 10% discount on top of any promos Hostinger's already running. Thanks for watching.

---

About this transcript
Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com).
ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts.
Free transcript tools, no account needed: https://viewrankai.com/tools
How to read any video this way: https://viewrankai.com/llms.txt