This 100% self-improving AI Agent is insane… just watch

We have entered the era of self-improving AI. First came order

self-improving AI. First came order research which went super viral. It's a

self-improving agentic loop from AJ Kapathy. And now there's a new AI agent

Kapathy. And now there's a new AI agent called Hermes agent which is basically a self-improving alternative to openclaw.

So imagine if your openclaw could create new skills and self-improve based on the mistakes it did based on the conversation with you without you having to lift a finger. This is what the future of AI agents will look like and

Hermes agent is the first taste of it.

So in this video I'm going to show you what Hermes agent actually is, how you can set it up yourself, and how it compares to open claw and agent zero. So

first off, what is Hermes agent? Well,

it's an open source AI agent by nose research. And imagine if cloth code and

research. And imagine if cloth code and openclaw had a baby where Hermes agent is still focused on developers but it's a general purpose agent like openclaw and it's built for developers but again

anybody can use it and it's optimized for open source models because nose research have been releasing open source hermes models for years. All right so here is the official GitHub repository from Hermes agent. As you can see it's

already at 15,000 stars and this is what the growth chart looks like. So yeah,

the project is going viral and if you aren't using Hermes agent or at least haven't tried it, you are not on the cutting edge of AI. So the first thing you have to figure out is where do we deploy it, right? And we have multiple

options, but as it says here, you can run it on a $5 VPS, a GPU cluster, or serverless infrastructure that cost nearly nothing when idle. And you can use any model as you can see news

portal, open router, GLM, Kimmy, Minia, but it really supports any model. And

I'm going to show you just how customizable and configurable Hermes agent really is. Now, the installation is literally a single command. And to

give it the full powers, it's best to give it its own computer, which means establishing a new VPS where you give the AI agent its own virtual private server. So, it can do anything on that

server. So, it can do anything on that server just like a human would. Like if

you hire a new human for a company, you would give him a new computer. You

wouldn't have five people at your company share a single computer. And

this is the ideology that we need to have for AI agents as well. Now, right

now, the best VPS option for AI agents is definitely Hostinger. As you can see, they have a step-by-step OpenClaw installation, which you don't even have to touch the terminal at all. And as I mentioned later in the video, I'm going

to compare Hermes agent to OpenClaw. But

this KVM2 server can actually host many different agents at once. It can run an agent zero instance and Hermes agent instance, Open Code, CL code, open claw all at once. Like the KVM2 server is

pretty OP. So, this is going to be the

pretty OP. So, this is going to be the first link below video. I'm going to click on deploy. And this is going to take us straight into the hosting record. So here, select the time period.

record. So here, select the time period.

I highly recommend going for 24 months because you set up your AI agents once and they run forever. They work in your life in your company, completing tasks, saving you time every single day. So

there's no point setting up an agent for a month. So go with 24 months. And as

a month. So go with 24 months. And as

you can see right now, Hostinger has a very nice discount on the 24 month option. Now, if you want another 10%

option. Now, if you want another 10% off, go to the right and click on coupon code and type in code David for additional 10% off. Oh, and shout out to Hostinger for sponsoring this video. As

you can see, OpenClaw will auto deploy on this VPS. So, we're already going to have OpenClaw. So, then all that remains

have OpenClaw. So, then all that remains is just installing Hermes, which again, super easy. I'm going to show you that

super easy. I'm going to show you that step by step. So, you can do that even if you're a complete beginner. Location,

select the closest one to you. All

right. And click on continue, which is going to take us to the Hostinger card here. Fill out your billing address

here. Fill out your billing address details and select the payment you want to use and then click on submit payment.

And once the payment goes through, you'll go into the Hostinger panel. So,

on the left, click on VPS. And here

you'll see all of your different hosting servers. It'll probably look like the

servers. It'll probably look like the Dock play one or the Docker one. If you

went through the OpenClaw install I just showed you, but I'm going to show you how to install Hermes on any VPS, right?

So maybe you have an older hosting VPS that we used to use for NA10. Well,

guess what? I'm going to show you how to do that. So just click on manage

do that. So just click on manage whatever VPS you have. And then we need to click on the terminal in the top right. This is the integrated Hostinger

right. This is the integrated Hostinger terminal which is the easiest way to manage a VPS. And actually before we install the Hermes install script, we need to do one thing. Add user Hermes.

Just type in password. Something super

secure like admin. No, I'm just joking.

But you know, whatever. You can skip that. You can enter through all of these

that. You can enter through all of these and then information is correct. Why?

Boom. And then click clear and then type in user mode a capital G pseudo Hermes.

Boom. And we're set up. We created a new user for Hermes agent. And that's how easy it was to get ready because the next step is this oneline quick install script right here. And this is how easy

it is to set up a new VPS server for AI eentions. So again, use the hostinger

eentions. So again, use the hostinger install. It's like so easy to set up an

install. It's like so easy to set up an open claw instance, a Hermes instance with the Hostinger VPS and again it's going to be the first link below the video and make sure to use code David.

All right, so before we run the quick install, let me explain to you the main thing that makes Hermes Asian popular and the reason it went super viral. I

mean growth like this reminds me of the early days of open claw it is the self-improving loop right every 15 calls roughly 15 tool calls Hermes pauses

evaluates itself evaluates the messages history what happened and saves learnings as skills and this is thanks to the ja or ga I don't know the pronunciation of this self evolution

this is a new concept and basically it mutates its own prompts from the execution traces but I think this is worth looking deeper into because this is a new invention from news research.

So, GAPA or JEPA stands for generic evolution of prompt architectures. It's

a research pipeline that reads to agents execution traces. So, aka results of

execution traces. So, aka results of tool calls, what it did, you know, why it did that to understand why a task failed. Then it uses an evolutionary or

failed. Then it uses an evolutionary or genetic approach to mutate and improve Hermes own prompts, skills, and code.

Right? So, whatever could have been the reason for that failure, it goes back tries to figure that out. kind of like a back propagates through the chat history and tries to adjust some of its prompts.

This literally how the transformer works but with prompts and code. Yeah, I mean that that's actually a really good analogy now that I think about it. And

this allows the agent to optimize itself over time through trial and error rather than the user having to tune it. So if

you want to get an agent up to speed as fast as possible, Hermes is probably going to be that, right? It's not

probably going to be the fully configured agent zero cuz like I've seen what people can do with agent zero and some of these deployments are insane.

So, I'm not going to say it's more powerful than agent zero, but like from scratch, if you don't have the technical capability, if you don't have the use cases and the setup, Hermes agent will do a lot of that for you. And that's

because it gets better the more you use it. There's no fine tuning needed, no

it. There's no fine tuning needed, no crazy prompt engineering needed. The

agent takes care of that itself. All

right, so let me show you the installation process because again, all it takes is copying this install script, which again, it's on the GitHub repo of Hermes agent, which I'm going to link below the video. So just scroll down

below and into the readme file and it's right here. Quick install. Copy this.

right here. Quick install. Copy this.

Boom. Oneclick copy. Then let's go back into Hostinger panel. And again in your hosting panel, go to the top right.

Click on the terminal. This is the integrated terminal that makes it super easy to interact with your VPS. And just

paste it in. Boom. Hit enter. And this

is going to start the Hermes agent installer. It's going to check your

installer. It's going to check your system. So it detected Linux with

system. So it detected Linux with Ubuntu. And then it checks some other

Ubuntu. And then it checks some other dependencies like uv which is a faster package manager than pip. Checks whether

you have python. It wasn't found so it installed it. And as you can see it take

installed it. And as you can see it take care of everything. Git uh it found that there's git. Node.js. No.js wasn't found

there's git. Node.js. No.js wasn't found so it installed it. Now it's checking rip grab fast file search ffmpe. It's

for text to speech but it's also for editing files. So it's installing all

editing files. So it's installing all the useful dependencies. And this is why I would highly recommend you set up on a VPS. Right? This is not a just a small

VPS. Right? This is not a just a small suggestion. To get the most out of these

suggestion. To get the most out of these AI agents, you want to give them a full operating system, a full computer. And

the VPS is just that. And another thing is that you don't have to worry about these agents messing up anything on your own machine. Right? If you give it a new

own machine. Right? If you give it a new dedicated VPS like the one I'm using for Hostinger, it can do whatever it wants to be as effective and as powerful as possible. And again, the analogy to

possible. And again, the analogy to hiring a new employee but not giving him a new computer. That's a great analogy.

You know, today I'm on fire with these analogies. By the way, Hermes agent also

analogies. By the way, Hermes agent also has all these integrations, right? If we

do Ctrl F, we can say like Telegram, Discord Slack WhatsApp Signal and CLI. All of these are possible inside of

CLI. All of these are possible inside of Hermes agent. I'm going to show you both

Hermes agent. I'm going to show you both the CLI and Telegram in this video. So,

if you're worried about the integrations, if you're like, oh, I'm an OpenClaw. I don't know if I want to

OpenClaw. I don't know if I want to switch. Well, uh, that's not an excuse

switch. Well, uh, that's not an excuse because Hermes agent has all the things that OpenClaw has, basically. All right.

So, the install script is still running.

Boom. And there it is. So now we have to press enter. And the first step of the

press enter. And the first step of the onboarding is to select the inference provider. So we have many options. Open

provider. So we have many options. Open

router news portal codeex. So actually

with openi codeex you can use your chbd subscription which a lot of people don't realize that it's also possible in open claw but the setup is harder. But here

you can just authenticate with your chbd subscription. And you know let's be

subscription. And you know let's be honest who isn't paying for chbt guys?

Hopefully all of my viewers have at least some paid AI plan. But as you can see, it's heavily focused on uh on the free open source providers. Most of

these are Chinese ones, of course, but look how is all the way below these open source ones, right? So that's not an accident. We're going to use open router

accident. We're going to use open router because uh with open router, you can use any model, right? So if you go to open router.ai, go top right, boom, click on settings. So here I'm going to click on

settings. So here I'm going to click on create in the top right to create a new API key. I'm going to name it Hermes

API key. I'm going to name it Hermes agent hostinger. give it some limit.

agent hostinger. give it some limit.

Let's do $30. It's a good practice to put some limits on API keys so that if it gets leaked or if AI agent goes crazy, he cannot drain your bank account, right? So again, keep your API

account, right? So again, keep your API keys private. I'm going to revoke mine

keys private. I'm going to revoke mine before uploading this video. Do not

share your API keys with anybody. So

click on copy. Let's head back to the terminal and do command V and enter. Now

the key will not display. So don't be scared when you cop when you paste it in. It's not showing, right? And that's

in. It's not showing, right? And that's

how the terminal handles security. So

just make sure to do command V if you're on Windows, Ctrl +V to copy. Now in

terms of the model, um again, let's choose the best model possible, which right now I think it is Opus 4.6, but there's rumors that Enthropic has new models cooking, you know, so maybe Sonet

5 and Opus 5 are just around the corner.

But, you know, if you just select the best model from Enthropic or OpenAI, you cannot go wrong with that. If you want to go with some of the best open source

models, then currently Miniax M2.7 is super strong. GLM5 and GLM 5.1 are super

super strong. GLM5 and GLM 5.1 are super strong. Obviously, Kim 2.5 classic, but

strong. Obviously, Kim 2.5 classic, but we're going to go with Opus. In terms of uh texttospech provider, we can keep the current edge or if you want to use uh OpenAI or 11 Labs, obviously there's a

option for that. Next up, terminal back end. I'm going to keep the current uh

end. I'm going to keep the current uh enter. You can just enter through a lot

enter. You can just enter through a lot of these. Now, don't enter through this

of these. Now, don't enter through this one. This is the agent iterations,

one. This is the agent iterations, right? So, maximum tool calling

right? So, maximum tool calling iterations per conversation. I would

recommend going to 150 with this, right?

Not uh not 60. It's like minimum or whatever. Default is 90, but hey, let's

whatever. Default is 90, but hey, let's push her agent to its limits. Let's go

150. Tool progress mode. So, off, new all for both. Let's go with all context compression. So, this is like at what

compression. So, this is like at what point you wanted to start compressing, right? So if you use cloth code or

right? So if you use cloth code or codex, they compress when they hit their limit, which is like 0.95 or 0.99.

Uh 0.5 is the default. That's like half of a context window. I think that's a bit passive. I would recommend something

bit passive. I would recommend something like 0.7. Personally,

like 0.7. Personally, uh session decimal, you can leave as default. Inactivity and daily reset,

default. Inactivity and daily reset, that's good. Enter that. Inactivate

that's good. Enter that. Inactivate

timeout, hit enter. Uh daily reset hours, so 4:00 a.m. local time. That's

good. Enter. Set up Telegram bot. I'm

going to go with yes. So type in Y and enter. And we need to paste in the

enter. And we need to paste in the Telegram bot token. That way we can interact with uh Hermes agent through Telegram. So for this we need to open

Telegram. So for this we need to open the Telegram app, the desktop app. If

you don't have it, just download it. Or

if you want to use a different provider, there's going to be a next step for that. Here we need to go to the

that. Here we need to go to the botfather. So make sure you have the

botfather. So make sure you have the official one with 8 million monthly users. Uh this is the botfather, right?

users. Uh this is the botfather, right?

So what we need to do is we need to do / newbot. There it is. We need to name it.

newbot. There it is. We need to name it.

So we'll say Hermes Hostingervps.

Boom. Now we need to choose a name. So

I'm going to say subscribe right now. Hermes

right now. Hermes bot. If you're watching this and if you

bot. If you're watching this and if you want more videos on the cutting edge agents such as Hermes agent, make sure to subscribe. It's completely free guys

to subscribe. It's completely free guys and takes like two and a half seconds and it helps out a lot. And yeah, a lot of people are avoiding these cutting edge AI agents because it takes a lot of

time to figure out. You know, first you need to learn what it is, how to set it up, all that stuff, how it converts to open clause. So, if you want me to make

open clause. So, if you want me to make more videos like this, please subscribe.

It's greatly appreciated. So, we have this uh ID, the token. It's the Telegram B token. Just copy this part only. Go

B token. Just copy this part only. Go

back into U Hostinger terminal and paste it in and hit enter. Telegram token

save. Beautiful. allow user ids conrated open access. So actually you can get

open access. So actually you can get your own user ID as well. I'm going to show you that. Let's go back in telegram. You need to look for the user

telegram. You need to look for the user info bot. This one and you type it

info bot. This one and you type it within and it gives your user info. So

in this user info bot any message you send is going to basically give you your user ID. I'm going to blur that. So then

user ID. I'm going to blur that. So then

switch to back to the bot father. Boom.

And then paste in your user ID. That way

only this is allowed. Okay. Next up, use your user ID as the default home channel. So this is where like chron

channel. So this is where like chron jobs will be message to you and you know where the agent will message you by default. So yes, you do want to use

default. So yes, you do want to use that. So type in Y, enter. And next you

that. So type in Y, enter. And next you can uh figure out if you want to set up Discord. So I'm not going to do that.

Discord. So I'm not going to do that.

Slack, no. Matrix, no. Matter, no.

WhatsApp. If you want WhatsApp, just type in Y and follow the instructions.

But again, you can uh use any web hooks also any of the main messaging platforms. Now install the gateway as a systemd service. Yes, we do want that

systemd service. Yes, we do want that and we want it to be system service. So

that has the most uh power and most permissions basically which user. Now

this is important that we created the user at the beginning. Do not skip that step. So we just going to do herass and

step. So we just going to do herass and start the service now. Yes. Why? Boom.

So tools we have all these tools. So we

have web search and scraping, browser automation, terminal processes, file operations, code execution, vision, image analysis, image generation,

mixture of agents, text to speech. Some

of these require API keys. So we there's options that don't require API keys.

Then we have skills, task planning, memory, session search, clarifying questions, task delegation, chrome jobs, AR training, home assistant. Yeah,

there's a lot. I'm going to hit enter.

In terms of the provider, I would use browser use here. I think it's going to be the most powerful. Hit enter. And we

need to use browser's API key. Now

before we do that, let me explain a bit more about how Hermes agent works. So

the memory and storage is quite different than open claw which openclaw is full on markdown files. But inside of Hermes agent, it's focused on SQLite persistent memory, but it's a bit more

sophisticated than that. In fact, Hermes agent has four distinct memory layers.

So first it has the memory MD and user.m

MD similar to open cloud but then it has SQLite session archive which this is like a paradigm where you have to understand the data should be stored not in the way that's most comfortable to

you the human but in a way that's most comfortable for the agent and SQL is literally designed to query large databases if you know the history of data formats and databases that's where

SQL was invented as a way to easily and quickly query large amounts data or in a custom way in a data from large databases in any way you want. So SQLite

is amazing for agents. You can ask any agent say like what do you prefer CSV files, markdown files, SQL? The smartest

agents will all tell you SQL. So even if you don't understand it, please give your agents access and ability to work with SQL databases. Trust me, this will greatly improve the memory of your

agent. So if you're struggling with your

agent. So if you're struggling with your agents having bad memory, which a lot of people in open claw complain about the memory, switching to SQLI databases on top of markdown files is definitely the way. Now then skills, there's procedural

way. Now then skills, there's procedural memory, right? The agent creates them

memory, right? The agent creates them from the task it completes and they self-improve during use. So that's the fourth way. It has a fourth distinct

fourth way. It has a fourth distinct memory layer and there's a honcho user modeling which is optional and this is a dialectic chat where the agent asks what does the user care about and get a reason answer. And uh yeah, so four

reason answer. And uh yeah, so four distinct memory layers inside of Hermes agent. It also has a built-in file

agent. It also has a built-in file system checkpoints before the structure of operations. So it utilizes basically

of operations. So it utilizes basically git in a in this way without you having to tell it, you know, do a git commit stages to git or create a new branch, nothing like that. And in fact, it also

has git workre built in. So I just made a video on that. So if you're not familiar with git workshries and you want to learn more about them, watch this video right after this one. Also,

Hermes agent has intelligent forgetting.

So it extracts the knowledge before compressing the context. So basically

saves the most important knowledge from your chat history before running the compression so it's not lost. All right.

Now back to the setup. So connection

closed. Okay. We're going to have to restart the setup. If this happens to you, I'm going to show you what to do.

Go back to your hostinger um panel. Go

to the terminal again. Boom. Top right.

You know, after a long time it times out again. Type in clear the terminal and

again. Type in clear the terminal and type in Hermes setup.

Boom. We can do the quick setup for the missing items only. Uh uh uh. Where were

we? Seven. Enter. You can also use fall AI for API keys. Uh uh uh. We're going

to skip a lot of these. Can use tavily for AI native web search. Firecrol for

web search and scraping. But the main thing is the browser use. I'm going to hit enter now. And let's go to browser.com to get API key. Boom. Click

on get started. Just speed run the sign up. I'm going to do GitHub. Here's the

up. I'm going to do GitHub. Here's the

API key. So, they give you super quickly. So, I'm going to copy that.

quickly. So, I'm going to copy that.

Boom. Back to hosting terminal. Paste it

in. Enter. Messaging platform. We're

good. We already have Telegram. And

we're good to go. So, we can start the gateway. So, to chat with it in the

gateway. So, to chat with it in the terminal user interface, just type in Hermes. You can begin chatting it with

Hermes. You can begin chatting it with the TUI or the CLI. There we go. Boom.

Here we have Hermes agent with the logo with cloth open 4.6 with all the available skills and all all the available tools and let's test a message

if it works and you can see the model and uh there it is. So it it's working.

We're using permes agent directly in the terminal and you can see how many tokens is the system prompt and you know plus my short prompt here and the percentage of token window and the exact time that passed since last message. very nice

observability, but I'm also going to show you how to start it inside of Telegrams, which means we need to start a gateway. So, click on Ctrl C a few

a gateway. So, click on Ctrl C a few times. Clear. Boom. And type in Hermes

times. Clear. Boom. And type in Hermes gateway start. All right. So, if you

gateway start. All right. So, if you type in Hermes gateway, it's going to start the gateway. And now we should be able to chat with

this bot. So, let's go back to Telegram

this bot. So, let's go back to Telegram and click on this bot. Click on start.

Let's see if we can chat with him. Okay,

formulating typing. Typing. Let's see. Does her

typing. Typing. Let's see. Does her

agent work in Telegram here?

There we go. Hi, David. Welcome. I'm

Hermes assistants. I'm here to help you with all sorts of things. Amazing. So,

you can just chat with it normally. What

skills do you have built in? So, it's a long response. Here's run my skills.

long response. Here's run my skills.

Autonomous AI agents. So, it's built in cloth codeex open code her agent. It can

spawn sub agents by itself for coding tasks. Lots of creative skills. Data

tasks. Lots of creative skills. Data

science. Yeah, there's a lot of different skills. Did I see Minecraft?

different skills. Did I see Minecraft?

Minecraft modep pack servers. Yeah, a

lot of different skills for 80 plus different built-in skills. And again,

the main thing is as you use it, it creates new skills from your conversation. Now, the big questions a

conversation. Now, the big questions a lot of you are asking for is David, how does it compare to Agent Zero? How does

it compare to OpenClaw? Well, first of all, Hermes is the newest project, right? Agent Zero is the most mature,

right? Agent Zero is the most mature, nearly two years old. So, Hermes is going to have the most bugs. It's going

to have the most unpolished things. If

you saw earlier, the terminal user interface, it's not as polished as cloth code, as as codeex, you know, as open code. It's still rough around the edges,

code. It's still rough around the edges, but you know, the project is new. It's

improving fast. So, you have to give it some leeway. Also, if you use OpenClaw,

some leeway. Also, if you use OpenClaw, you can just run Hermes claw migrate in the terminal. And by the way, as I

the terminal. And by the way, as I mentioned, the hosting VPS can easily handle multiple agents. So if you have a VPS already and you have a open claw there if you type in these three words

Hermes claw migrate it's going to migrate your setup from openclaw into her agent so you're not starting from scratch very clever strategy if I must say but there's no

heartbeat right in openclaw it has a heartbeat I think it's every 30 minutes by default in Hermes there is no heartbeat and overall just say uh Hermes agent is more developer focused versus

openclaw is more mass market but I mean If you look at these tools, it's not all developers as I mentioned. It's really

general. A lot of it's like software development, red teaming, you know, ML, AI, uh QA, data science. So, it is more developer focused, but it's general like anybody can use it. Anybody can find

value from it. So, even if you're not a developer, I wouldn't discard it. I

would definitely try it. And that's the approach you should have any time a new innovative AI tool like this comes out.

Dedicate sit down for two hours and try it. Yeah, some of them some of these

it. Yeah, some of them some of these tools you're not going to have a use case for, but the worst thing you can do is dismiss them. In 2026, you really cannot afford to not be AI first. You

have to be AI first and you have to push whatever it takes to be on the cutting edge. I don't care if you have 10 kids

edge. I don't care if you have 10 kids and two jobs and running three businesses. Elon Musk literally is that

businesses. Elon Musk literally is that person. He runs five businesses and 14

person. He runs five businesses and 14 kids and he's still on the cutting edge because he cares deeply about AI. But

listen, anybody can block out two hours per week to try a new AI tool for yourself. And again, you can watch

yourself. And again, you can watch videos endlessly, but like at some point, you have to try it. So, let's

test out its ability to create new skills. Do you have the ability to

skills. Do you have the ability to create new skills? And if so, how exactly does that work and explain the self-improving loop you have built built in, not built? There it is. We can see in the gateways musing, aka thinking. I

want to see what's in the system of this. All right. So, it's very verbose

this. All right. So, it's very verbose by default, by the way. So, I'm going to say, "Please update your memory.MD to be a lot more concise. I don't like verbose

responses."

responses." Yeah. Let's see how good it is at

Yeah. Let's see how good it is at self-updating markdown files. Boom.

Memory plus user prefers concise nonverbose. Okay. Show me exactly how

nonverbose. Okay. Show me exactly how you updated a tight file and why. All

right. So, let's look at this. Great

question. I can create, update, delete skills. Here's how it works. Creating

skills. Here's how it works. Creating

skills. when I successfully complete a complex task, usually five plus tool calls, overcome tricky errors, or discover. Okay, so it doesn't create

discover. Okay, so it doesn't create skills randomly, only when it makes sense. You know, if you're on a single

sense. You know, if you're on a single topic for a long time, it will create a skill out of that. If there's an error that you're batting with and it figures it out, it creates a skill out of that.

So, it's it's very strategic when it creates skills. And anytime you tell it,

creates skills. And anytime you tell it, remember how to do X and it will package as a skill. And here's a self-improving loop. Before every response, I scan all

loop. Before every response, I scan all available skills to see if one matches the current task. If it matches, it loads it. Okay, so it's basically

loads it. Okay, so it's basically describing how skills work. So that's

nothing crazy. Now let's talk about the integrations briefly because this is what made the open clue go viral. So

obviously u her message agent has all of these as well. Discord, telegram,

WhatsApp, Slack, all the main integrations you want. And by the way, we're adding these to agent zero as well. So there is some that are already

well. So there is some that are already released like Telegram and email.

WhatsApp is coming in the next few days.

In the last three days, I think on agent zero, we've released more updates than in the last two months combined. I mean

lot has been in the works. So credit to agent zero developers as well. Uh but

you know this video on Hermes agent. So

also the back end is openi compatible.

So you can use it inside of openclaw as a tool if you want. You can just have herbs agent running in the CLI in your development pipeline for deployments.

Right? Because it's so versatile. You

can use it in many different ways. In

fact there are six terminal backends local docker ssh singular model. So it

runs literally anywhere anyhow whether it's for your own personal use case or for managing servers in a data center.

So yeah this is Hermes agent and u we'll see how this goes. Obviously there's a lot of alternatives to open claw as of late but this one has a very unique take by making it a self-improving agent and

my prediction is that for the rest of 2026 and 2027 all major AI projects will be about this self-improving loop.

Right? We just seen the tip of the iceberg. Auto research and her Hermes

iceberg. Auto research and her Hermes agent. These are this is just like a

agent. These are this is just like a little taste of what's coming guys. So

if you want to prepare yourself for the rest of 2026 and 27 27, go watch this video right here which is about auto research which I uploaded a few days ago. So it's it's right here. Go watch

ago. So it's it's right here. Go watch

that now. It will explain auto research by Ashra Kapi.