100 hours of Hermes Agent lessons in 46 minutes

My name is David Andre and here are the seven levels of Hermes agent. While most

people only have a very basic setup, in this video I'm going to show you how to set up Hermes agent so it's actually useful and very very powerful. In the

first level, we will go over the fundamentals. I'll show you how to

fundamentals. I'll show you how to install Hermes agent on a dedicated VPS.

In the second level, we will integrate Discord. We will set up a custom Discord

Discord. We will set up a custom Discord server and create a new Discord bot specifically for your Hermes agent. In

the third level, we will set up Hermes curator. This is a new thing inside of

curator. This is a new thing inside of Hermes agent that compacts the autogenerated skills. I'm going to show

autogenerated skills. I'm going to show you how to set it up so you can save on tokens. In the fourth level, we will

tokens. In the fourth level, we will talk about automations and chron jobs and how to set up Hermes agent so it automatically backs up itself to GitHub every single day. In the fifth level, we will take it further. We'll talk about

the new canban board built into Hermes agent. So you can visually see how it's

agent. So you can visually see how it's progressing on tasks and you can give it different tasks in different stages just like you would if you had a full team of developers. In level six we will talk

developers. In level six we will talk about advanced memory system. We'll set

up holographic memory for Hermes agent.

We'll take it a step further on how to give Hermes agent what's basically infinite memory. And in level seven we

infinite memory. And in level seven we will turn Hermes agent into a full backend. will expose it as an MCP server

backend. will expose it as an MCP server so that your cloth code your PI agent your codeex can interact with Hermes agent build on top of it delegate tasks to it as if it was a full MCP back end.

Now I've been following Hermes agent very closely since the first few days it came out in February paying attention to every major update. I've also personally spent thousands of hours using different

AI agents from Cloud Code to Codex to PI agent to OpenClaw to Hermes agent and I'm one of the few people who actually practice what they preach. I built a whole AI startup vectal from zero to

155,000 ARR just by using AI agents like cursor and cloth. And currently I'm spending between 6 and $10,000 per month on just API costs for AI agents. So in

this video you're not going to get some unproven theories or hypothetical scenarios. I'll show you how to actually

scenarios. I'll show you how to actually set up Hermes agent and how to make it powerful in seven different levels where each level makes it more and more powerful building on top of the previous

ones. And don't worry, you don't have to

ones. And don't worry, you don't have to be a DevOps expert or a developer to do this. As long as you have a computer,

this. As long as you have a computer, access to internet, and you can speak in English, you can absolutely follow this tutorial. So, if you watch until the

tutorial. So, if you watch until the end, you're going to have a more powerful Hermes agent setup than 99.9% of people. Now, the first thing we need

of people. Now, the first thing we need is a VPS. That way, the AI agent can live on its own computer. I think the best option by far is Hostinger. This is

what I use for all of my AI agents and automations. And it's also one of the

automations. And it's also one of the most affordable options out there. So,

I'm going to leave a link to this landing page below. And as you can see, they have a dedicated Hermes agent setup to make it as easy as possible. So, go

right here, click deploy. And again, the link to this page is below the video.

And here, select the length of the plan.

I would recommend going for 24 months, but minimum 12 months. The reason is simple. You set it up once and the AI

simple. You set it up once and the AI agents keep running forever. And with a single VPS, you can use Hermes agent, Open Claw, agent zero. You you can put your N810 automations in there. You can

host your full full stack web app on a VPS. You can do all of that on a single

VPS. You can do all of that on a single KVM2 plan. So that's why I recommend

KVM2 plan. So that's why I recommend going for 24 months. Plus, you get the biggest savings if you go for 24 months.

Now, if you want to save even more money, go to the right and click on have a coupon code and type in code David.

Hostinger was kind enough to sponsor this video. So, if you use the code

this video. So, if you use the code David, you'll get an additional 10% off your Hostinger plan. Then, scroll down, select the server location. I'm going to go with Lithuania and click on continue.

This will take you to your hosting record where you need to put your credit card information and complete the checkout. Now, it's going to take a few

checkout. Now, it's going to take a few minutes for your VPS to set up. Usually

2 to 3 minutes from my experience. So,

in the meantime, we can look at the official Hermes agent GitHub repo which has 133,000 stars. Pretty crazy growth if you ask me. In fact, it's one of the fastest growing open source projects in

history. Now, what the team behind

history. Now, what the team behind Hermes did is that they created everything into a single quick install command. Right? So with hostinger we get

command. Right? So with hostinger we get a option of deploying this inside of docker container which is good for security but personally I prefer running on the root level which luckily it's very easy. You just copy this oneline

very easy. You just copy this oneline installer and run it in the terminal.

All right let's go back to hostinger where the VPS has finished setting up and we're going to do that using SSH.

And again you don't even have to understand what SSH means. You just need to know hey I copy this command and this is going to be used to access my virtual private server from my own computer. And

then when you open the terminal, you simply copy this SSH command and you paste it in. Boom. It's asking, are you sure you want to connect? I'm going to do yes. And then it's going to ask for

do yes. And then it's going to ask for our root password. And again, if you manage to forget this, no worries. It's

very easy to do a reset in Hostinger.

Just click here, root password. Click on

change and click this button to generate the password. It will generate a new

the password. It will generate a new secure password for your VPS. All right.

Seems like the password has changed.

Let's open the terminal again and paste that in. Boom. And here we go. We're

that in. Boom. And here we go. We're

logged in into our VPS. You can type in clear to get rid of this mess. So now I can control what's happening on my virtual private server. And this is important because it allows me to do things like installing Hermes agent on

root level. So when I go back to the

root level. So when I go back to the GitHub repo, which again I'm going to link this below the video, you can just copy the quick install command.

Literally click right here to copy the full thing. Go back to the terminal and

full thing. Go back to the terminal and paste it in. Boom. And this is going to install all of the dependencies that Hermes agent needs to run on your VPS.

So, if you don't have your own VPS in 2026, go below the video, click the first link. It's going to take you to

first link. It's going to take you to this hostinger page and set up your own VPS. All right, let's check the

VPS. All right, let's check the terminal. Okay, so it's finished

terminal. Okay, so it's finished running. Let's go with the quick setup.

running. Let's go with the quick setup.

Hit enter. Now, we need to select the inference provider, aka how do we use AI? How do we access AI? Now, as you can

AI? How do we access AI? Now, as you can see, there's a lot of options, right? Uh

news portal. It's from the developers behind Hermes. We can also use open

behind Hermes. We can also use open router enthropic lm studio if you want to run the models locally and have it completely private or you can use for example openi codex which allows you to

use your chbd subscription to run her agent for free right so if you have if you're paying for chbd plus or chigbd pro you can literally use that subscription to power hermes agent but personally I'm going to use open router

because allows you to use any model possible next we need to give it an open router API key so I'm going to go to open router.ai AI. Go to top right, click on credits. Oh, make sure to create an account. It's completely free,

but you need to charge a couple of dollar of credits. Um,5 or $10 should be enough. You don't need 88. Go to top

enough. You don't need 88. Go to top left, click on API keys. And then go to top right and click on new key. Let's

name it seven levels of Hermes. And I'm

going to put some credit limit like $30 should be enough. And I'm going to create. Now again, do not share your API

create. Now again, do not share your API keys with anybody. Obviously, I'm going to rotate this key before uploading this video. I'm going to copy and go back to

video. I'm going to copy and go back to the terminal and paste it in. You need

to click and paste it in. It will not be showing because it's a private key. So

don't be surprised by that. It doesn't

show the characters here. You can select any type of model available on open router. This is why I like to use it.

router. This is why I like to use it.

There's so many models. But I'm going to go with Opus 4.7 which is Enthropics latest model they give us, you know, to ask public um the ple. Okay. So actually

uh this is the next level. So I'm going to skip that. I'm going to show you Discord in a second. Launcher chat now.

And yes, we can test chatting with it.

Okay, there it is. Hermes agent loaded on our very own VPS. You can see the list of available skills here, but I'm just going to send a message. Hey,

and let's see if we can get a successful response. There it is. Hermes agent

response. There it is. Hermes agent

running cloth opus 4.7 on our very own VPS. So, this is level one completed.

VPS. So, this is level one completed.

Real quick, anyone who joins the new society during the month of May will receive a personalized audit of their GitHub repository. And you can actually

GitHub repository. And you can actually tell us what to focus on, whether it's security, architecture, front- end design, code quality, or just leave this empty and let us look at it. A lot of you people who get into AI coding, they

have no idea what they're doing, and they have no idea if their GitHub repository has any flaws, issues, or obvious things they're missing. That's

why for the month of May, anyone who joins the new society will receive this as a bonus, a personalized GitHub audit.

Plus, we have a new course about Hermes agent. So, if you like what you're

agent. So, if you like what you're seeing in this video and you want to take it a step further, make sure to join the new society, go to the classroom and go through the Hermes mastery course. The link to new society

mastery course. The link to new society is going to be below the video. Now,

level two is connecting Hermes to a chat messaging tool that you already use, right? So, you can use it from the

right? So, you can use it from the comforts of WhatsApp, Slack, Telegram, Discord, iMessage, whatever you're already using, you can use Hermes from that. And for this video, I'm going to

that. And for this video, I'm going to use Discord. So, let's switch back to

use Discord. So, let's switch back to our terminal. I'm going to hit Ctrl C to

our terminal. I'm going to hit Ctrl C to kill this process. So you need to hit Ctrl C a few times. I'm going to type in clear to get rid of everything and make it clear. And I'm going to Hermes

it clear. And I'm going to Hermes gateway setup. Enter. This will allow us

gateway setup. Enter. This will allow us to set up further things about the gateway. You can see how many options

gateway. You can see how many options there is. Even Microsoft Teams, right?

there is. Even Microsoft Teams, right?

Like some of you might be using Microsoft Teams. It's kind of crazy, but if you are, you can use Hermes agent in your Microsoft Teams. Even email, right?

I'm going to go with Discord number two.

Hit enter. And we need Discord B token.

Now, Hermes agent gives us exactly where we need to go. So, copy this URL to the Discord developer portal. Open a new browser tab and paste it in. So, when

you paste this, uh, it's going to open the developer portal. In the top right, click on new application. I'm going to name it seven level Hermes. I know, very creative. By the way, if you want me to

creative. By the way, if you want me to make more videos on Hermes agent, make sure to subscribe. It's completely free subscribing on YouTube and it tells me, hey, you I should make more videos like this one. So, if you want your YouTube

this one. So, if you want your YouTube recommendations to be useful AI content instead of just wasteful entertainment, make sure to go below the video and click the subscribe button. It takes 2 seconds. It's completely free and it

seconds. It's completely free and it helps out a lot. Appreciate it. Okay, so

I'm going to click on create to create the new Discord app. It's asking me if I'm human. Okay, maybe maybe I'm not,

I'm human. Okay, maybe maybe I'm not, but I'm going to click that I am because we need it for Hermes agent setup. And

here we are. Okay, so we can obviously rename the bot and we can give it an icon. Yes. So, I'm going to use my own

icon. Yes. So, I'm going to use my own custom software to select a cool icon for Hermes agent. Let's go with this one. By the way, if you want me to

one. By the way, if you want me to release this, comment below. Um, we use this internally for anything YouTube related thumbnails titles sporting outlier videos. But again, right now

outlier videos. But again, right now it's only available to my team. So, if

there's enough interest, maybe I'll turn it into a commercial product. We'll see.

Let's go back to the developer portal and let's select the icon. There we go.

apply and save changes. All right. So,

if you look in the terminal, what Hermes needs, it needs the Discord bot token.

So, go to the left, click on bot, and scroll down and reset the token. Yes, do

it. It's going to ask for 2FA if you have it. Just paste in your 2FA code.

have it. Just paste in your 2FA code.

Boom. Submit. And again, keep this token private. Do not share this with anybody.

private. Do not share this with anybody.

I'm going to copy it. I'm going to paste it directly into Hermes. Here on this page, if you scroll down, we have these privileged gateway intents. We need to enable all three of these, right? So,

presence intent enable, server members intent enable, and message content intent enable. And then click save

intent enable. And then click save changes in the bottom right. Now, on the same page, you also need to give the bot some permissions, right? So, whatever

you want it to do, such as send messages, pin messages, embed links, attach files, read message history, send voice messages, whatever you want your her message to do, just enable them

here. Then go to the left, click on OF2

here. Then go to the left, click on OF2 and scroll down here. And we need to give it two things. We need to give it the bot scope and then applications commands. These two. Make sure to enable

commands. These two. Make sure to enable these two underneath O of URL generators. And then scroll all the way

generators. And then scroll all the way down. As you can see, it gives you a

down. As you can see, it gives you a generated URL. Copy that. Then open a

generated URL. Copy that. Then open a new browser and paste that in. This is

going to invite this uh bot to a Discord server, right? So let's click on allow.

server, right? So let's click on allow.

But to complete this step, you need your own Discord server, which if you don't have it, let me quickly show you how to set it up because it's very, very easy.

So, inside of the Discord UI, go to the left and click on add server. Here, I'm

going to click create my own. For

friends and me, I'm going to name it recording server. Something simple, and

recording server. Something simple, and click on create. And just like that, in a matter of 5 seconds, I managed to create a new Discord server, which I would recommend you to do because then

you can use the server for all of your different Discord bots for AI agents. So

now if we rerun the same link, we should be able to invite Hermes agent into the recording server. There it is. And click

recording server. There it is. And click

on authorize. Okay, nice. On the right, we can see that our seven level Hermes has been invited to the Discord server.

Beautiful. Now, if you remember correctly in the terminal, it's asking for my username, right? So inside of Discord, if you click on your uh profile in the bottom left, you can see copy

user ID. If you don't see it, you need

user ID. If you don't see it, you need to open user settings and type in developer. Okay, developer on the left

developer. Okay, developer on the left or maybe like advanced settings or something. One of these two options. But

something. One of these two options. But

basically, you need to enable developer mode right here. And then if you click on your profile picture, you will see this button, copy user ID. Click that.

Go back to the terminal and simply paste it in. Hit enter. It's asking for the

it in. Hit enter. It's asking for the home channel. Uh you can leave it empty.

home channel. Uh you can leave it empty.

So just hit hit enter. And that's it.

Done. Install the gateway as a systemd service. We can do yes. Hit enter again.

service. We can do yes. Hit enter again.

Start the service now. Yes. Enter. Okay.

It is online now. Beautiful. Our board

is online. So we say if we tag it seven love hermes. Hey, we should hopefully

love hermes. Hey, we should hopefully get a response. Okay. We have have the eyes emoji. This means that Hermes has

eyes emoji. This means that Hermes has seen the message. And if we click here into the thread, there it is. It

responded here. Amazing. So I can maybe say like who are you? There it is. It

has the eyes. I'm Hermes. Yeah.

Assistant. I can help you with coding, research, drawing, script, browsing the web, managing files and a bunch of other stuff, right? And when it completes, it

stuff, right? And when it completes, it gives you the check mark. So that's how you know Hermes agent is working and it's responding. So we have level two

it's responding. So we have level two completed. Now let's go to level three

completed. Now let's go to level three of your Hermes agent setup and that is setting up the Hermes curator. This is a new thing released in the last couple of days that basically makes sure that your skills don't stack up. Right? So if the

self-improving loop creates skills that never get used, they will mark them for deletion after 30 days. And if they're not used for more than 90 days, it will delete them so that you don't get context rot so that your Hermes isn't

bloated with skills that never get activated. First, let's go back to our

activated. First, let's go back to our terminal so we can access our VPS again.

I'm going to type in clear and type in Hermes update so that you update to the latest version of Hermes agent. All

right, there it is. It says update completed. There it is. It restarted the

completed. There it is. It restarted the Hermes gateway. And now we can type in

Hermes gateway. And now we can type in clear and to check the status of your Hermes curator if you already have it enabled. Hermes curator status. As you

enabled. Hermes curator status. As you

can see, it is enabled and the settings are as follows. So, obviously, we can change all of these if needed, but realistically, the default settings are pretty good. If a skill isn't used for

pretty good. If a skill isn't used for more than 30 days, it's marked as stale and if it's not used as 90 days, it's deleted. So, make sure you have curator

deleted. So, make sure you have curator enabled because people who don't, they just pay for wasteful tokens, right?

That can be thousands of dollars. In

fact, for me, it is thousands of dollars because I'm using so many different AI agents. And it's going to make your

agents. And it's going to make your Hermes agent more focused and less distracted. Okay, let's talk about level

distracted. Okay, let's talk about level four, which is schedule tasks, also known as chron jobs, also known as automations. This lets Hermes agent

automations. This lets Hermes agent automate things on a schedule, right?

So, it could be once a day, every other hour, once per month. But this is very, very powerful. And I'm going to show you

very powerful. And I'm going to show you a use case that all of you should set up no matter what you're doing. And that is daily backups to GitHub. So by the end of this level, you'll know how to create any type of automation inside of Hermes

Agent, giving you the ability to save endless amounts of time in either your life or business. The first thing we need is of course a GitHub account, which is completely free. So go to github.com and top right, either sign

into your existing account or sign up for a new one. I already have a GitHub, so I'm going to log in. There we go. And

then make sure to create a new repository which you can either do here by clicking new or by clicking top right and going to repositories and then clicking the green button new right

here. I'm going to name it something

here. I'm going to name it something like test Hermes backup. Very simple

private repo for my Hermes agent backups.

Boom. Here just make sure to put it as private. Okay, very important. You don't

private. Okay, very important. You don't

want your backups to be visible to the internet. And then click the green

internet. And then click the green button create repository. And just like that, you just created your own GitHub repo in a matter of 15 seconds. Nothing

to be scared about. GitHub is absolutely essential in 2026. Now, inside of GitHub, we also need to create a personal access token so that Hermes can somehow access this GitHub repo because remember we made it private, right? So,

go to top right, click on settings.

There we go. Settings. Go to the left, scroll all the way down, and click on developer settings right here. Then on

the left click on personal access tokens fine grain tokens and generate a new one. We can name it something like um

one. We can name it something like um seven levels Hermes backups owner expiration. You can you know set

owner expiration. You can you know set no expiration or 7 days up to you. And

then you can only select certain repositories. We're going to select the

repositories. We're going to select the Hermes backup. There it is. So it cannot

Hermes backup. There it is. So it cannot mess with other repositories. Then we

need to add some permissions. So click

on add permissions. Scroll down and find contents and then put read and write because it needs to read the GitHub repo but also write to it daily. Okay. So now

click on generate token.

There it is. Generate token

and here it is. So now what we need to do is we need to open the terminal again sshed into the VPS and type in Hermes config set and then the name of the

environment variable. Let's do something

environment variable. Let's do something clear like GitHub token, you know, GitHub token and then space and copy this um personal access token and paste

it in. Boom. This will securely store it

it in. Boom. This will securely store it into the environment file enviring Hermes to use it, but it's not going to be sent to the AI. I'm going to open Hermes and I'm going to tell it, listen,

I just uh set up a new token in our env file. I don't want you to read it. I

file. I don't want you to read it. I

just want to check it if it's there and uh try doing something with it to see if it works or not. File exists. The token

variables are and yeah, it's the GitHub token. Okay, it's asking uh for

token. Okay, it's asking uh for permission. I'm going to allow it. It

permission. I'm going to allow it. It

works. Beautiful. So now let's create the chrome job so that every single day at night automatically back up itself into GitHub. Right? So if you remember

into GitHub. Right? So if you remember we had this repo and this repo is empty now, right? Nothing is on there. so that

now, right? Nothing is on there. so that

if something goes wrong and if your VPS explodes or your Hermes agent deletes everything, your data is still safe on GitHub. Now, one thing you should check

GitHub. Now, one thing you should check inside of Hermes agent is the status of the gateway if it is installed as a systemd service. That way, it can run

systemd service. That way, it can run 24/7 and that's very simple. You just

type in Hermes gateway status, hit enter, and as you can see, systemd linger is enabled. Beautiful service

survives logout. That's amazing. So,

let's do clear. And I'm going to give it this prompt to set up the daily backup.

Right? So very simple prompt. I want a daily freem backups of the entire Hermes folder to my private GitHub repo. And

this is the name of the repo we just created. Right? Test Hermes backup.

created. Right? Test Hermes backup.

The token is GitHub token.

I want to read the prompt, but it's already doing it. Please set the Git identity Hermes B. Clone the repo.

Create daily Chrome job at 3:00 a.m.

Prague time. And uh yeah, it's just telling it what to do, right? And then

uh run it once to see if the push works.

So it's going to run it once. GitHub

token isn't in the environment. It's see

the token is in there. Actually, look

deeper.

I don't know why it's having trouble uh looking into the token. Yeah, found it in Hermas. Let me verify it loads. Okay,

in Hermas. Let me verify it loads. Okay,

update your memory so that you remember where the env file actually is located.

Okay, backup ran committed push successfully. Let's reload.

successfully. Let's reload.

And here we go. Here we have our first backup from today of the entire uh folder which is 60 megabytes. It's above the

GitHub limit.

Um so to optimize it, we could only back up certain things. But I'm going to also send this message so it remembers the location of these tokens. And now the chrome job is created here. This is the

ID scheduled at 3:00 a.m. um Central

Eastern European time. And the next run is tomorrow at 3:00 a.m. So now Hermes agent is going to back itself up. It's

probably not needed to back up the full thing every day. If you want to just back up your skills only, you can say, "Hey, just make sure to back up my skills only or only my markdown files, right?" So you're probably um going to

right?" So you're probably um going to have faster backups and not like spamming your GitHub repo with the full thing. But if you want the full thing,

thing. But if you want the full thing, um you can also back up the the entire thing, right? Again, just talk to it in

thing, right? Again, just talk to it in plain English. That's enough. So now you

plain English. That's enough. So now you know how to create scheduled tasks aka Chrome automations with Hermes agent.

This is level four. Now let's go to level five. Now level five is really

level five. Now level five is really cool. This is one of the biggest

cool. This is one of the biggest releases to Hermes agent recently which says a lot because there are releases nearly every day. Like literally every other day the team behind Hermes agent

pushes a major update which is crazy.

But this one is especially insane because first of all it went very viral but second of all it allows you to run multiple AI agents through a canv board.

So the way it works is that the agents claim tasks from this canban board and they work in parallel. Right? So let me show you this graphic and you as the human you simply watch in a simple user interface instead of having to have 20

terminals open you just look at the canban and you manage okay this task is in progress this task getting started or this agent is working on that task like a window into the future. All of us are going to have hundreds of AI agents

working for us much sooner than you realize. So what's going to matter is

realize. So what's going to matter is how do you manage these agents? How do

you actually have clear observability and clarity of what they're doing? That

is going to be a billion dollar question because whoever figures this out is going to help build a multi-billion dollar company, right? And obviously

Hermes is trying to do that right now and they're actually adding it into Hermes agent. So this is level five.

Hermes agent. So this is level five.

Let's set it up. Now, one of the best things about working with AI agents like Hermes is that you can literally ask it to set this things up for itself, right?

Boom. A link to that release and literally telling it help me set this up. For context, Hermes agent now has a

up. For context, Hermes agent now has a multi- agent via canban in the UI. At

first, it activates the skill Hermes agent. Then it checks the skill cannib

agent. Then it checks the skill cannib orchestrator and it goes to this URL with browser navigate and it's going to read it and learn everything about the release and it's going to tell me what it needs from me and the remaining

steps. It's going to do it itself.

steps. It's going to do it itself.

Right? So here it learned everything.

You already have Hermes latest update.

Beautiful gateway running. Can been

initialized. You're missing the specialist profiles. So, it's asking for

specialist profiles. So, it's asking for the specialist profiles. I'm going to say just set it all up. You have my permission. Okay. It's asking too many

permission. Okay. It's asking too many informations. Obviously, if you want to

informations. Obviously, if you want to customize it, feel free to tell it like I want a researcher or I want this to be for software development or social media research or something else. In this

case, I just wanted to set it up and stop overthinking. Also, I'm going to

stop overthinking. Also, I'm going to say update your memory to always responds in a super concise and clear way. Now, one important thing I want to

way. Now, one important thing I want to stress is that do not use cheap models.

Okay? These agentic harnesses like Hermes agent or openclaw, they are complex. They're very complex. And if

complex. They're very complex. And if

you cheap out and you try to use a very small, very cheap model, you're going to have a hard time. Okay? So, to get the most out of Hermes agent, use something like Opus 4.7, GBD 5.5. Don't be cheap.

Okay? Don't use small model. use the

most powerful model available. So as you can see Hermes agent is doing a lot like dozens and dozens of terminal commands to set this up himself right like I just

said okay I want this release I want this multi- aent canban orchestration dashboard and uh that's it you know Hermes is setting it up I was asking for a command task these are the boards

already okay what is this command secure this can okay let's allow it and this is the beauty of it being on a VPS you don't have to worry that it's going to do something sketchy on the computer it has its own computer which I think It's

the ultimate paradigm where each agent runs on its own computer so it can set it up in a way that it needs to be most effective. The dashboard loads and now

effective. The dashboard loads and now it's testing the dashboard itself.

That's crazy. Look at this. Wow. It

navigates to the local host on the VPS.

It clicks around, takes a screenshot of it and it's it's debugging itself.

Okay, man. This is impressive. Browser

vision.

This is the difference between Hermes agent and something like CHBT, right?

Catch me absolutely cannot do these things. Launch a local host server

things. Launch a local host server inside of itself and then click around and take screenshots of it and debug it.

Man, this is wild. The dispatcher is working. Let me grab a screenshot for

working. Let me grab a screenshot for David. So, it saved the memory and then

David. So, it saved the memory and then it said the Canon setup is done. Four

profiles default researcher, writer, reviewer. And the dashboard is there.

reviewer. And the dashboard is there.

And it even gives me the SSH to view it from my laptop. That's insane. I haven't

even asked for this. That was going to be my next prompt. I literally have it prepared. I have the prompt prepared for

prepared. I have the prompt prepared for it to give me the the link for the SSH tunnel, but it predicted that itself. And it

even included a screenshot of what this looks like on the VPS, guys. This is

crazy.

This is this insane. We really do live in the future. All right. Well, uh,

let's do this, right? So, actually, I'm going to give it the Let's go back to Hostinger panel. And then I'm just going

Hostinger panel. And then I'm just going to take a screenshot of this whole thing. And I'm going to say update the

thing. And I'm going to say update the SSH tunnel command to actually include my VPS address. Okay, I don't even want to bother figuring this out. I can just

screenshot my full screen, send it to Hermes agent and tell it, yo, figure it out. Tell me what to do. You know what?

out. Tell me what to do. You know what?

What is the server IP and figure it out?

Okay, copy that. And let's open the terminal again. We need to actually open

terminal again. We need to actually open a new terminal. Command N. Paste that

in. Root password again. So hopefully

you saved it. Boom. Let's paste that in.

And here we go. We're in. And then we can just open this. And we are in the Hermes a Asian canban. So on the left, it's a bit small, but on the left you can see canban right here below plugins.

Click that. And this is the canban.

Okay. So you can drag stuff around, change it up however you want. Just like

in any canban board, right? Whether you

use trellot, monday.com, clickup, whatever, you can manage how your Hermes is working. and dispatch multiple Hermes

is working. and dispatch multiple Hermes agents on different tasks. Now again, I really have to stress this. Hermes set

this up by itself for most part like it ran for like 3 minutes, 4 minutes, then done all these commands and set it up by itself. I just gave it the link to the

itself. I just gave it the link to the release say like this is a cool release.

I just want this. Help me set this up and it literally did everything itself.

And now we have the canban here installed. We can click new tasks, you

installed. We can click new tasks, you know, set up rough idea, research the new latest update of Hermes agent. Boom.

We can create that. Maybe let's do something in to-do. Help me set up a multi- aent workflow with codeex so I can build and deploy apps on Versel by

itself. Let's put something in blocked.

itself. Let's put something in blocked.

Help me set up a new office in Katavita Poland. I already did that but you know

Poland. I already did that but you know just example as a as a thing and uh these tasks are getting automatically moved to ready and Hermes is ready to work on them. Okay, but this is cool and all but how do you actually make it

useful? Well, let me show you a use case

useful? Well, let me show you a use case that I myself actually need and that is research for content. And in fact, all of you can do this um just apply to your

own business or to your niche. Right?

So, let's go back to Discord and let's paste in this prompt. It's pretty long because I described exactly what I mean want. I want to make a YouTube video

want. I want to make a YouTube video about uncensored AI models, right? And

again, let's say you want to make a LinkedIn post about how to hire people in Germany. Whatever you do, whatever

in Germany. Whatever you do, whatever your business is about, whatever you want to research, just give it a task. Okay? Describe the

task. You don't have to copy my own example, but I'm doing something that's truly useful for me because a lot of people, they're just incompetent in terms of giving these agents use cases.

There's like literally such a large percentage of population that have openclaw set up, but they don't use it because they don't know how. They have

Hermes agent and they know how to set it up, but they don't know what to give it.

So, here's a clear example.

Cue this as a four task canban pipeline on the default board. You must use canman create. Basically I'm telling it

canman create. Basically I'm telling it you know that it should use the cananban because you know sometimes it just completes itself but this is all about the canban board right the new update.

So I wanted to be using it. So I send this detailed prompt and now her agent is doing that. If we reload we could see some changes happening.

Okay we already have the changes. We can

see draft three research. There it is in progress research state of unsca models.

You can click on it to get more info.

priority zero size priority assign researcher status running. So the it created four different profiles of four different AI agents and now the researcher one is working on it. You can

see where it lives on the workspace created by the user. You can see these all different options trash ready block unblock archive the description of this task. What's the state of uncensored

task. What's the state of uncensored obliterated jailbroken AI models right now? Cover the topics, dependencies,

now? Cover the topics, dependencies, parents, comments, events, worker log, very detailed. And you can even send

very detailed. And you can even send comments on this task as it's running.

So basically, here is how that works, right? You have the first researcher,

right? You have the first researcher, what's new in topic this week? What's

new in fitness, in real estate, in AI?

Then the second researcher, what's already on YouTube about topic in the last 30 days? And these run in parallel, right? Then the analyst waits for the

right? Then the analyst waits for the first two to find a gap, right? some

angle, something that people are missing. And then the fourth agent, the

missing. And then the fourth agent, the writer, drafts three video concepts after the third one finishes, right? So

this is a very simple workflow of multiplayer agents working at the same time. And we have the canban to actually

time. And we have the canban to actually monitor their progress, right? So

obviously Hermes agent can do this even without the canban. But the way the canban is useful is allows you the human, it allows you to see what's happening, right? Not just looking into

happening, right? Not just looking into terminal with endless commands and lots of text. This is a very visual way to

of text. This is a very visual way to monitor the progress of your Hermes agent and all the different sub agents.

All right, so let's check what the status is. We can see that uh everything

status is. We can see that uh everything is moved to complete and we can even see these tasks and we can either click on them and inspect um here or you can go

to discord and chat with it chat with her here. What is the status on these

her here. What is the status on these tasks? Give me a concise report.

tasks? Give me a concise report.

So we can check it itself. And by the way, here we can see a lot more things than just the canban. We can see the different sessions we have as well as whether they're in Discord CLI or somewhere else. We can see our current

somewhere else. We can see our current automations, schedule jobs. Boom. This

is the GitHub one. You can see boom. We

can also see the documentation if something is um you know lagging or something isn't set up correctly. You

can check the logs. You can check the models that are available and the usage on them. How many tokens total total

on them. How many tokens total total spent different analytics about Hermes so this is very useful but let's uh check in discord all tasks done yes show me the full output and show it here

again Hermes gives you this nice u gateway dashboard and you can even uh restart gateway from here or update Hermes or you can just chat with it through discord for maximum convenience because you know you have discord in

your phone or WhatsApp or telegram whatever you prefer and that's the power of DC agents they're so configurable so extensible that uh anybody can adapt them to their own um use case or their own preference.

The issue is that most people don't know what their preference is or don't know how to how to configure them. But

luckily you're watching this video so you hopefully at least know how to configure them and if you are smart you can figure out a few use cases for Hermes agent. All right here is the

Hermes agent. All right here is the answer. As you can see it's a quite long

answer. As you can see it's a quite long answer.

Concept number one uncensored coding agent use a 2427B model into clo okay fair enough explained Eurabes finding that one

direction any LLM's confus refusal the bench off okay so specific ideas with clear pre-production for all of them not bad

not bad so this is level five using the Hermes canban to manage AI agents and what tasks they're working on okay so level six is adding memory because a lot of people struggle with AI just not

having good long-term memory and losing context and stuff like that. So, here's

why memory plugins like holographic actually exist. Beginners never save

actually exist. Beginners never save anything, right? They just chat and u

anything, right? They just chat and u they hope that the default memory is good enough and obviously in Hermes it's probably better than in any other agent.

But beginners don't even trigger that with words like remember this or save this into memory. So everything stays in the chat and dies at the end of the session. I think most of you probably do

session. I think most of you probably do that mistake as well. I certainly did it when I was newer to AI. Also, bigger

context doesn't mean more memory. People

who are like one step, two steps ahead of beginners, they just paste in a bunch of slop, right? And a lot of it is not even relevant to what needs to be done.

So, more context doesn't necessarily mean it's going to be better memory. But

more context always results in more cost and worse attention to the things that matter the most. Right? A lot of people then go to rack retrieval augmented generation but that's by vibes you know vector simulator cannot answer what does

that have it own like what what's my own um task what's my own responsibility that needs structure you know you don't see what task assigned to each person just from similarity just from semantics

now embeddings also cost money and they leak data you know if you use Gemini embeddings you are sending it to Google and summaries they blur over time you know they compress essential facts away

So most people have no idea how to solve this and this is why things like holographic exist. So in level six we

holographic exist. So in level six we give our Hermes agent near infinite memory. Okay. So to set up this near

memory. Okay. So to set up this near infinite memory let's jump back into our SSH and type in Hermes memory setup. Hit

enter.

As you can see it comes with a few pre-made options and holographic is one of them. You can try other ones like

of them. You can try other ones like horn show me zero open viking super memory. Um some of them require API key.

memory. Um some of them require API key.

As you can see, holographic is fully local and that's a important thing because then you're not leaking your data. You're not sending your data to

data. You're not sending your data to any cloud and obviously you don't have to pay for stuff. SQL database path. I

think that's good. Hit enter.

Auto extract facts at the session end.

You can either enable it or disable it.

I would enable it if you want maximum memory.

Default trust score for new facts. I

would put like 0.4 dimensions. Leave that as it is. Enter.

dimensions. Leave that as it is. Enter.

And that's it. Next, type in her mess gateway restart just to make sure that the gateway picks up everything.

And then we can type in her mess and then in the chat we can say something like check this to see if we have the fact store. Yes, holographic memory is

fact store. Yes, holographic memory is set up and working. All right, amazing.

So we can do something like read all previous sessions as well as user.m MD

and memory MD and seed the holographic back store so that it can add some of these things that we discussed in previous sessions or some of these things that it already knows about me

into holographic because you know we just set it up so it's obviously empty for now. Okay, so it analyzed all

for now. Okay, so it analyzed all previous sessions and now it's preparing uh so it did these tool calls to learn everything about me and what we talked

about and now it's doing u rightes into holographic fact store and we can actually maybe even prepare a prompt

like from now on remember to store anything important into holographic fact store. Okay, it see 15 facts my name

store. Okay, it see 15 facts my name that my preference discord CLI concise style responses. This is good.

style responses. This is good.

I mean yeah this is basically all we discussed but it it removed the useless stuff and only saved the import things.

All right so I'm not going to say um remember to store anything important in holographic fact store from now on and it's going to save it into the main memory so that it's actually

going to be using it. Now let's talk about a few use cases of why having solid memory actually matters in case it's not obvious. Number one, you can say something like remember everything

about each video you're making. Right?

So for me, if I use Hermes dedicated to YouTube, I would be running something like that. Remember the key facts about

like that. Remember the key facts about each video we're making. If it's a sponsor, if there's a deadline, what angle we're taking, what went wrong. So

it can be more useful with each video going forward. You can also track your

going forward. You can also track your sponsor history to know which a which of the sponsor paid what. Right? So the

agent would be in track of this. You

don't have to remember it in your head or track it in a spreadsheet. The agent

will be tracking that. It can also recall your VPS setup. You know um how much disk space you have, how much RAM you're using, all that stuff. It can

proactively check it manually. That's

another great um Chrome job you should create. It's like a weekly check of your

create. It's like a weekly check of your VPS to see the health. You know, maybe you're running out of space, maybe your your RAM is getting out of control. Who

knows? It could also catch itself when it's holding two facts that contradict each other, right? Because it will be in the memory. It see like, okay, we upload

the memory. It see like, okay, we upload videos every 5 days and there's a different one that says every 3 days.

Well, guess what? It's contradicting and it can ask you which of these is correct. And you can find connections

correct. And you can find connections between topics you've worked on that you don't even realize, right? So maybe

shorter videos perform better or sponsored videos get less views, whatever, right? Things that like

whatever, right? Things that like actually can have meaningful impact on your life or business. So, while most people just rely on the basic memory inside of Hermes, which isn't bad, holographic takes it to the next level

and makes the long-term memory a lot better. All right, level seven, the most

better. All right, level seven, the most advanced level obviously turning Hermes agent into an MCP. Okay, so basically you expose it as an MCP server so that other agents like Cloudcore or Codex can

interact with it as if Hermes was your back end. And this has three main use

back end. And this has three main use cases. Number one, serving as a remote

cases. Number one, serving as a remote approval gate. So let's say Cloudcore

approval gate. So let's say Cloudcore wants to run something destructive, right? A risky operation, deleting

right? A risky operation, deleting files, you know, removing database backups, whatever. You have like a hook

backups, whatever. You have like a hook that makes it pause. Hermes pushes the approval prompt to your phone so that you know, let's say you're on a date with a girl and now suddenly you do something important like, oh you know, my Hermes agent is messaging me.

It wants to push a risky update to delete a database. So maybe like, okay, this is a database backup. It's

obsolete. It's from 6 months ago. You

approve it. Or if it's something it shouldn't do, you reject it, right? and

then it continues. So this is the use case that cloth code cannot do like cloth code couldn't do this. It it

doesn't have access to your telegram or discord. It doesn't have these

discord. It doesn't have these connections these authentications. So

that's one use case. The second one is walk away mode. So you start a long refactoring cloth code and you close the laptop and you get progress pings on your phone right and you can reply like keep going you know make it simpler fewer lines of code or push to GitHub

whatever and you can trash from your phone as well you know. So bug report lands in discord. You can tell claude through Hermes agent to look at the relevant file and reply with a freeline diagnosis without opening your laptop.

So this is pre-made use cases of turning Hermes agent into MCP and is the most advanced level because most people don't even understand MCPS and they definitely do not even know that it's possible to

turn Hermes agent into an MCP server.

But I'm going to show you how to do that just now. So just like before, we're

just now. So just like before, we're going to set it up by just talking to Hermes and telling it to set it up. So

I'm going to do / new to start a new conversation. I'm going to paste in a

conversation. I'm going to paste in a very long prompt I have that starts with expose your Hermes to cloud code via MCP. So cloud can read and send messages

MCP. So cloud can read and send messages across your connected messaging platforms. Telegram, Discord, Slack, while you code editor. And there's 22 more lines. Let me just show you the

more lines. Let me just show you the full prompt. Here's the full thing. Feel

full prompt. Here's the full thing. Feel

free to screenshot it so you have the full prompt. Boom. There it is. So

full prompt. Boom. There it is. So

Hermes exposes the gateway so that cloth code which obviously can use MCB servers because Enthropic invented the model context protocol can interact with Hermes which otherwise it couldn't interact and obviously access all the

things that Hermes has configured already. So let's go to the terminal.

already. So let's go to the terminal.

Let's see how Hermes is doing on this task. Loop is closed. Okay say make your

task. Loop is closed. Okay say make your answer simpler and shorter. I'm not

reading all that. I don't know why Opus 4.7 is silver boss. Okay. Hey, Hermes

MCP works.

Okay. So,

tell me how to now test it on cloud code.

I will set up cloud code on this VPS, which obviously we still need to do yet because we haven't set up cloud code CLI on the VPS. Hermes is giving up the steps. So, yeah, let's do that. I'm

steps. So, yeah, let's do that. I'm

going to actually open in fact, I'm going to I'm just going to copy this and follow in the in the Discord because why not, you know?

So I'm going to copy this. Go to

Discord. I'm going to start a new chat.

Let's say U MCP a new thread. So it's create a separate.

Boom. Let's go to this thread.

I'm going to give it everything here as a context.

Context.

Help me set this up on my BPS. One step

at a time. Be very concise.

Boom. Let's send this. And then here in the terminal, we can hit Ctrl C to stop this and clear and follow these instructions to set up um cloth code.

Right? So, first we need to install cloth. So, let's copy this command.

cloth. So, let's copy this command.

Boom.

Installing cloth code. It's similar to the Hermes agent command we ran at the start, you know, a oneliner installer that's going to install everything. So,

there it is. If we do cloth, it should ask us to login. We need to reload the reload the thing, right? The shell. I'm

going to copy everything. I'm going to say what now super plain English like I'm literally showing you how to debug right using one AI agent which is Hermes agent

to set up cloth code so that we can then expose Hermes as MCP. It needs to add to path. So I'm just going to copy this

path. So I'm just going to copy this literally super simple debugging. And

there it is. It works right. So I'm

going to do clo and we need to authenticate dark mode is fine. Let's do

enthropic console account going to give us a link. Boom. Let's paste that into a browser.

Authorize.

We need to copy this code. Switch back

to terminal and paste in this code.

And that should be it. Login successful.

Enter. Enter. Enter. Just press enter three times. And let's type in message

three times. And let's type in message to see if cloud code is working. And it

is working. That was very easy. Enropic

has made this authentication super easy.

So I'm I'm here. So I can just say um SSH. Boom.

SSH. Boom.

I've managed to install cloud core and login. What now?

login. What now?

Right. So, we need to register the MCPU.

So, let's copy these two commands.

Switch back to our terminal. Hit Ctrl + C to kill the Hermes U TI. Let's run

these.

Okay. So, that's that.

Okay. I did these two commands. What

now?

Literally plain English debugging, right? Just make sure to use the best

right? Just make sure to use the best model you can. Don't use a cheap small model. So I'm using open 3.7 here. And

model. So I'm using open 3.7 here. And

uh now we start cloud code again. So I

can do cl- dangerously skip permissions.

Okay. It cannot be run in root whatever.

Just let's do normal cloth. Hit enter

and let's see what tools it has through the Hermas MCP.

All right. So it gives all of these uh different tools. MCP Hermes attachment

different tools. MCP Hermes attachment fetch Hermes channel list conversations get okay so test this actually get the previous conversations and uh you know

read some messages and see if it actually works these MCP servers so again plain English telling it to test the Hermes MCP let me load the tool

schema first then test them okay let's this is why I wanted to add to run in dangerous escape permissions so we don't have to approve these Yes,

both tools work perfectly. Here's the

summary. Conversation returned three Discord threads. Messages read

Discord threads. Messages read successfully read 10 messages channels list. Okay, everything works. Works

list. Okay, everything works. Works

nice.

Okay, so now use these tools to analyze things about me as a user. What am I likely missing? What are my attributes?

likely missing? What are my attributes?

What are likely my goals? Based on these conversations, based on these messages, what can you tell about me? Make sure to use the Hermes MCP for this and be very concise. Okay, let me read all three

concise. Okay, let me read all three conversations for a fuller picture and it's calling the Hermes MCP. Here's what

the conversation reveal. You're a

content creator.

Okay, Vectal. It even knows the company name. Power users self-host AI infra.

name. Power users self-host AI infra.

Okay, so listen, I'm not claiming to be power user. It's cloth code calling me

power user. It's cloth code calling me power user. Your behavior patterns

power user. Your behavior patterns delegates fully. Low tolerance for

delegates fully. Low tolerance for verbosity. That's true. checks in hours

verbosity. That's true. checks in hours later rather than monitoring. Okay. Your

goals, build a gen, produce YouTube content, automate everything. Yeah, I

mean it's true. It's basically use the Hermes MCP to analyze myself and uh obviously the power of this is that as you're building something, cloud code doesn't need to have all the context of your Hermes agent. You can keep it

private on a VPS. Maybe cloud code is on a different VPS or cloud code is running locally and it can still fetch the data when needed through Hermes because Hermes agent can be served as an MCB server which again most people have no

idea because they don't go through the seven levels of Hermes agent. Now if you watched all of this the next step is to actually go through the video again and set it up. So go below the video, click

the first link and get your very own virtual private server. Hostinger has

the one of the most affordable options for a VPS and it's super easy setup for Hermes agent. This is what I was using

Hermes agent. This is what I was using in the entire video. So again, click the first link below the video and get your own hosting or VPS. Make sure to use code David for additional 10% off. And

if you are serious about AI, then make sure to join the society. Everyone who

joins in the month of May will get a personalized audit of their GitHub repository. So you submit your GitHub

repository. So you submit your GitHub repo and we look at it. We can go through the security through the front end, suggest new features, whatever you want us to focus on or if you just want us to go through the whole thing without

any focus. You don't need to include

any focus. You don't need to include anything. But this is only available for

anything. But this is only available for people who join in May because it's not scalable to do this forever. It takes a lot of time to audit these GitHub repositories. So if you join new society

repositories. So if you join new society in May, you get a personalized GitHub audit. Plus in the classroom, we're

audit. Plus in the classroom, we're releasing a new course on Hermes agent.

So if you like this video, it's just a taste of what's coming in the classroom, right? So inside of new society, you get

right? So inside of new society, you get more granular step-by-step modules with pre-made resources, configs, skills, system problems that you can just copy paste into your life and business. So if

you want more access and more content about Hermes agent and also calls with me, which by the way, there's literally a call happening in 7 minutes. That's

why I'm speaking fast. Make sure to join the new society. The link to the new society landing page will be below the video. With that being said, thank you

video. With that being said, thank you guys for watching and have a wonderful, productive week. See you.

productive week. See you.