Big Idea

The argument in one line.

Hermes's newest updates turn it into a real multi-model orchestration hub, and getting value from it means building one bot per underlying AI model rather than copying the role-based bot setups other tools use.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…

You already run Hermes agent, or a similar open-source AI agent, and haven't kept up with its newest features.
You juggle multiple AI models (Claude, GPT, Grok, a local model) and want one place to manage a bot for each instead of switching apps.
You want a concrete answer to which AI agent handles which kind of task, not just a single 'best agent' pick.

SKIP IF…

You've never used Hermes agent or a comparable multi-model agent tool, since the video assumes you're already inside one.
You're looking for a single best AI agent recommendation. The whole argument here is that no one agent wins every job.

TL;DR

The full version, fast.

Hermes agent shipped ten updates worth changing your setup for. Bot mode now lets you run multiple bots at once, but the video argues the winning move is one bot per underlying model (a GPT bot, a Claude bot, a free local-model bot) rather than one bot per job role like Grok's setup encourages. New local-model support auto-detects your hardware and sets up a free model for simple tasks. A floating HUD keeps a screen-aware agent on top of any app, including games. ChatGPT-style voice mode now controls the whole multi-agent setup, a spoken 'Hey Hermes' wake word triggers hands-free delegation, sub-agents get a visible per-model interface, and cron jobs now remember what they researched last time instead of repeating it. The closing recommendation: pick agents by task type, not brand loyalty, using each tool's actual strength.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →

Chapters

Where the time goes.

00:00 – 00:29

01 · Cold open

Promises ten new Hermes features and a look at the creator's full multi-agent setup.

00:29 – 02:52

02 · Bot mode

Hermes bot mode lets you run multiple bots at once. The video argues against copying Grok's role-based bots and for one bot per underlying model instead.

02:52 – 03:55

03 · Advanced local model support

A one-click setting detects your hardware and configures the best free local model to run inside a Hermes bot.

03:55 – 04:54

04 · Sponsor: HubSpot AI agent cheat sheet

A sponsored segment for a free HubSpot guide comparing seven major AI agents by cost, setup difficulty, and best use case.

04:54 – 06:38

05 · Hermes HUD

A floating, screen-aware overlay that stays on top of any app, including games, and can answer questions based on what's on screen.

06:38 – 07:59

06 · ChatGPT-style voice mode

Voice control now works across the whole multi-agent setup, letting a spoken request orchestrate and delegate to other bots.

07:59 – 08:38

07 · "Hey Hermes" wake word

A spoken wake word triggers hands-free task delegation without switching windows or apps.

08:38 – 10:04

08 · Sub-agents UI

Multi-part tasks now spin up visible sub-agents, each showing its assigned model and full activity log.

10:04 – 11:06

09 · Improved cron jobs

Recurring cron jobs now remember what they researched previously, so daily tasks stop repeating the same ground.

11:06 – 13:06

10 · Which agent for which task

A recap of the creator's own stack: ChatGPT for deep technical work, Grok for general knowledge on mobile, Hermes for cross-computer and personal admin work.

Atomic Insights

Lines worth screenshotting.

The mistake with Hermes bot mode is copying Grok's approach of making bots by job role; the better move is one bot per underlying model.
Hermes's real advantage over closed agents is that any bot can run on any model or provider you choose.
A one-click 'run models locally' setting inspects your hardware and picks the best free model to run, whether it's a 16GB Mac Mini or a high-end workstation.
Even a weak local model is worth running for simple tasks, since every query on it is free.
The Hermes HUD is a floating overlay that stays on top of any app, including full-screen games, and can see what's on screen.
A screen-aware HUD can answer in-game questions like where to find a specific boss because it reads the screen directly.
ChatGPT-style voice mode inside Hermes can now orchestrate and delegate to other bots by voice, at roughly 5 cents a minute.
Talking through tasks the moment they occur to you and handing them to an agent verbatim produces more delegated work than typing them out later.
A spoken 'Hey Hermes' wake word lets you fire off tasks hands-free while multitasking, without switching windows.
Sub-agents in Hermes now get a visible per-model interface, so you can assign Claude to one sub-agent and GPT to another on the same job and compare results.
Cron jobs in Hermes now retain memory of what they researched last time, so a daily research job stops repeating the same ground.
No single AI agent wins every category: the video's own split is ChatGPT for deep technical work, Grok for general knowledge on mobile, and Hermes for cross-computer and personal admin work.

Takeaway

Build bots around models, not job roles

AGENT WORKFLOW

Hermes's real advantage is letting you run one bot per underlying model and route tasks by each model's strength, instead of copying role-based bot setups from other tools.

02Bot mode

Build one bot per underlying model (Hermes/GPT, Claude, a local model) instead of one bot per job role, so each bot inherits that model's actual strength.
Route tasks by model strength: coding-heavy builds to a strong reasoning model, front-end work to whichever model handles design best, throwaway tasks to a free local model.
Ask the agent itself to create new bots in bot mode instead of configuring each one by hand.

03Advanced local model support

A one-click local-model setting inspects your hardware and picks the best free model to run, from a modest laptop to a high-end workstation.
Even a weak local model is worth running for simple, low-stakes tasks, since every query on it is free.
Local model support turns any computer into a source of unlimited, if lower-quality, intelligence for background work.

05Hermes HUD

A persistent on-screen overlay keeps a screen-aware agent available on top of any app, including full-screen games.
Screen-aware assistance turns an agent into real-time contextual help mid-task, instead of a chat window you have to alt-tab to.
Keyboard shortcuts to toggle a floating agent HUD instantly mean it never has to interrupt whatever you're doing.

06ChatGPT-style voice mode

Voice control now works on top of a multi-agent setup, so one spoken request can orchestrate and delegate to several other bots.
Voice interaction is fast enough to replace typing for delegating tasks, at a cost of a few cents per minute through an API key.
Talking through tasks the moment they occur to you, then handing them to an agent verbatim, produces more delegated work than typing them out later.

07"Hey Hermes" wake word

A spoken wake word lets you fire off tasks to an agent hands-free while multitasking, without switching windows or apps.
Voice-triggered delegation works best the moment a task occurs to you, before it's forgotten or deprioritized.

08Sub-agents UI

Multi-threaded tasks can spin up visible sub-agents, each showing which model it's running and a full window into what it's doing.
Assigning different models to different sub-agents on the same task lets you compare outputs side by side before picking one.

09Improved cron jobs

Recurring automated tasks that retain memory of what they covered last time stop repeating the same research on every run.
Memory-aware recurring jobs make daily research compound in usefulness instead of resetting every run.

10Which agent for which task

No single agent wins every category: pick by task type, not brand loyalty.
A practical split is deep technical work to the tool with the best desktop harness, general knowledge lookups to whichever agent has the best mobile app, and cross-computer or personal admin work to an open-source agent willing to touch multiple machines.
An open-source agent's core advantage is model flexibility and full customization, not raw individual capability, so lean on it specifically where those advantages matter.

Glossary

Terms worth knowing.

Bot mode: A Hermes feature that lets a user create and run multiple distinct bots at once, each with its own model, memory, and personality, managed from one interface.
Hermes HUD: A small floating window that sits on top of every other app on screen, giving instant access to an agent that can see and respond to whatever is currently displayed.
Sub-agent: A secondary agent spun up automatically to handle one piece of a larger multi-part task, running under a visible interface that shows which model it's using and what it's doing.
Cron job: An automated task set to run on a recurring schedule, such as a daily research report, without a person triggering it each time.
Local model: An AI model that runs on the user's own computer instead of a remote server, so it costs nothing per use but is limited by the device's hardware.

Resources

Things they pointed at.

04:00toolHubSpot's free AI agent cheat sheet ↗

00:00channelShip It Weekly (newsletter) ↗

00:00productVibe Coding Academy (Hermes bootcamp, Skool) ↗

00:00productHenry Intelligent Machines ↗

00:00productCreatorBuddy.io ↗

Quotables

Lines you could clip.

01:17

“Now with Hermes bot mode, you have multiple bots, different profiles, different memories, personalities, tools, all of that. But here's the mistake I see a lot of people use with this new feature.”

sets up the video's central contrarian claim→ TikTok hook↗ Tweet quote

05:42

“It's like the best cheat code for video games ever.”

short, punchy, visual claim about the HUD→ IG reel cold open↗ Tweet quote

10:16

“Now the memories of those cron jobs have improved... it even says previously researched.”

concrete before/after proof point→ newsletter pull-quote↗ Tweet quote

11:22

“There's a lot of guardrails on the other AI agents when it comes to that.”

differentiator claim for open-source agents→ newsletter pull-quote↗ Tweet quote

The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

metaphoranalogy

Hermes Agent has released some monster updates lately that have completely changed how you use the AI agent. If you use these new, sometimes hidden features the right way, you're going to be a productivity machine. In this video, I cover all the new features and show you my brand new Hermes Agent setup.

I also show you what I'm using. Am I using Grokbot, Hermes, ChatGBT, and which tasks I use them for. If you stick with me until the end of the video, you'll be a master of the best open source AI agent out there.

Now let's lock in and get into it. So one of the biggest updates from Hermes lately is the bot mode Here is how you need to be using the bot mode for those who don't know Grock bot comes out a couple months ago Takes the world by storm Hermes quickly comes out with their bot mode. What is the bot mode?

Bot mode allows you to create multiple Hermes bots very, very easily and manage them and talk to them all at the same time here. Sort of like iMessage. Previously, Hermes was very much a single agent setup where you just talk to one agent.

It's just kind of the god mode agent that does everything for you. Now with Hermes bot mode, you have multiple bots, different profiles, different memories, personalities, tools, all of that. But here's the mistake I see a lot of people use with this new feature.

They treat it like Grok. where they make a whole bunch of bots that all are like different human roles, the developer role, the marketer role. I don't think that's the right way to do this.

I think that's fine for Grokbot. For Hermes, you want to make profiles and agents that kind of match the strength of what Hermes is. And the strength of what Hermes is, is you can use any model, any provider you want with each one of these agents.

So I'm not making agents that have different roles. I'm making agents with Hermes, which is G. GPT -6 Ash, Claudie, which is Opus 5.

I'm making agents for all the different models so I can take advantage of the strengths of each one of those models. If I need to build something, I go to Hermes, my GPT -6 Astra model. If I need some front -end work done, I go to Claudie.

If I have simple tasks I want done, I go to Quen, which is actually powered by a local model running on my DGX Spark. So it gets it done completely for free. So my recommendation to use this, go to your Hermes agent, say, hey, set...

me up a new bot powered by Claude or whatever other models you want to use hit enter it will set up the new bots for you in the bot mode by the way this is only in Hermes desktop and all you have to do is click the bot mode here and it will create the new bots for you do that then you can use the strengths of each model for whatever task you're doing if you want to do cheap coding make sure you make a Grok bot in there.

If you wanna do super fast coding, I actually make a Meta bot in there. Meta's coding models are actually good now. So make sure you set those up.

We're actually gonna be covering 10 awesome new features here. So let's get to the second feature, which is their advanced local model support. Now, stay with me here.

It doesn't matter which computer you have, this local model support's gonna be relevant for you. So I really, really like this. If you go to settings and then you go to providers and then.

you click on run models locally click that what's going to happen is it's actually going to look at your hardware and then determine the best local model you should be running on it doesn't matter what you have you have a Mac mini 16 gigabyte you have a super powerful Mac studio like me does not matter it will figure out the best model for your device and then basically manage it for you.

All you need to do is click set up for me. It'll almost be like LM Studio where it'll download it for you, load it, test it, run it, and it'll put it into a Hermes bot for you. So you will have your own Hermes bot powered by a local model with unlimited intelligence.

Now I'm gonna be honest, if you have a bad computer, if you have a smaller computer like a Mac Mini, will it be the best intelligence in the world? No, but you'll still get free intelligence. So even if you have a smaller computer, You can use it for really simple tasks to let it run and do it for free.

So everyone should be doing this now. Go to providers, local models, and see which local model it wants to load for you. And then loadups, click set up for me.

You have nothing to lose by doing this. Hermes agent is insanely powerful, but it's just one piece of the agent puzzle. Luckily, my friends over at HubSpot put together a free AI agent cheat sheet that helps you figure out which AI agents should be used for which jobs without having you need to test a bunch of tools yourself.

Inside the guide, it covers seven of the biggest AI agents right now. ChatGPT agent mode, Manus, ClaudeCowork, OpenClaw, Zapier, N8n, ClaudeCode. For each one, it breaks down what it's best at, how hard it is to set up, what it costs, and when you should actually use it.

You also get copy paste starter prompts. These prompts cover workflows like competitor research, lead routing, and daily briefings. So you can go from comparing tools to actually using them right away.

is the skip if you need section which basically tells you hey these agents you don't need to use them if you do these there's so many agents out there it's good that they tell you which ones you don't need to use if you enjoy hermes you want to know what other agents you should be using too this is the resource for you grab the free cheat sheet in the link down below and thanks to hubspot for sponsoring the video the next big update i've been using on is hermes hud this is a great new feature especially if you play video games this is like a gamer's dream i recently built like an open source version of this for all my other agents, but it's great that Hermes built this in.

So basically it allows you to make this like kind of mini version of Hermes. This little HUD, you can move it anywhere on your computer you want. It always sits on top of whatever's on your screen.

So if you open up a game, you open up War Dogs or World of Warcraft, whatever you're playing, this will sit on top of it. So anytime you can go in and you can talk to it, you can say, hey, what's the stock price of... MU Micron, but here's the cool part.

It has access to whatever's on your screen So if you're playing a game you're playing World of Warcraft and you're on a quest you're stuck You don't know where to go. Maybe as you kill like a specific like high -level elite boar You can go in on Hermes Hut and say hey, where is this boar located? It'll show you'll tell you exactly where to go because it can see your screen So it's like the best like cheat code for video games ever If you had a Game Shark when you were a kid like me, I know my millennial is showing right now.

This is basically like that, or just an easy way to access your agent no matter what's going on your screen. You don't have to keep minimizing, opening and minimizing. It's just always a HUD that's there working for you.

So I love it. If you're on Mac, all you need to do is do Command -Shift -H. If you're on Windows, it's Control -Shift -H.

puts it in HUD mode and you're good to go. You can move this around anywhere on your screen you want, and you always have Hermes agent ready to go. It's amazing.

Which brings us to feature four, which is it now has ChatGPT voice mode. If you've watched my previous videos, you know I am absolutely in love with ChatGPT voice mode. I think it's such a powerful tool.

Well, guess what? You now can hit this button right here, open it. Hey, can you tell me what the status of my other agents are?

So it has the strengths of ChatGPT voice, which is, It's real -time, interacts with you very, very quickly, but it also has access to all its tools. So it can look what your other agents are doing.

It can orchestrate your other agents. It can delegate tasks to different agents. It's basically ChatGPT Voice, but in this nice multi -agent setup.

All you need to do is put in your OpenAI API key and it's good to go. I think the costs are like really small. It's like 5 cents a minute or something like that.

So it is really, really cheap and it's really awesome. If you haven't used ChatGPT Voice yet, it is such a sick way to use AI. It is clearly the way of the future, the way we'll be interacting with computers in the future, which is through our voice.

I recommend when you're doing work next time and you're thinking about typing your Hermes agent, just use voice instead. Sit there, talk to your microphone, and just delegate tasks out. Just stream a conscious as you come up with tasks, give it to your Hermes agent, and now it'll be amazing at delegating it to your different bots you set up, which is...

Much related to the next feature I really love that they just released, which is the ability to use the Hey Hermes keyword to talk to your agent. So as you can see here, I just said it out loud. Hey Hermes, can you tell Claudie to build a 3D first person shooter using 3JS?

And as you can see, it... gave the command to the other agent to build the 3D first person shooter. So now basically anytime you're sitting at your computer and you think, oh, I wish I could do this, I wish I could do that, you just say the Hermes keyword and it starts listening to whatever you have to say.

This is awesome. You're multitasking, you're sitting at your computer, you think of things, you say the keyword and you just start shouting out tasks to do. It's been really helpful for me.

I've been able to get way more done. I'm telling you, voice makes you so much more productive. The next feature I'm really enjoying is its sub -agent functionality.

It now has really nice user interfaces for sub -agents so you can track what each sub -agent is doing. A lot of the AI agents out there and tools, they don't give you visibility into all the agents. I really like this.

So check this use case out. Please use sub -agents to design three concept poster images for a dystopian shooting video game called Null District. It's a stylistic cyberpunk dystopian looter shooter.

What's going to happen when you give it task that has multiple threads and strands to do, it's going to spin up a bunch of sub agents, but now it's going to give you a really nice interface for them. As you can see here, here are the three different sub agents.

You can see which models they're using. You can click in and you get an entire window with every single thing the agent is doing, which is really cool. If you want to change each sub agent, which model they're running.

So maybe you want to do like Claude for one sub agent to see what kind of design you get. Muse for another, you can go in here and do that. You can change which scale.

bills each sub -agent uses, things like that. That's like the strength of Hermes, right? It's so configurable.

You can do anything you want, any model you want, any provider you want. So I highly recommend doing that. When he uses sub -agents, have it use different sub -agents.

Have it use Opus, have it use ChadGBT, have it use Grok and see how the different sub -agents perform. Really good if you want to do something like design related where you can see different options after it's done. The next feature that's great is the cron jobs are greatly improved.

Now have memory of past Cron jobs. So if you're anything like me and you have your agents do regular research, daily research, weekly research, whatever, it will now remember its past research and not. repeat its research again.

So as an example, I have it research AI stocks every day. I like to invest, I like to invest in AI companies. Before it would go and it basically research a lot of the same companies over and over and over again, because it had no memory of its past cron jobs and what it did during those cron jobs.

Now the memories of those cron jobs have improved. So now you can see here. Here's one of the research reports I did recently where I went through, found a bunch of stocks, Micron, Micron, AVGO.

But if we look at the next report. It researches an entirely different set of companies. As you can see, it even says previously researched.

It shows it right there, which is amazing. So now your cron jobs are a lot higher quality. I'd recommend doing all your research cron jobs inside Hermes because now it has that memory, which is really, really nice.

So I think the number one question I get in all my videos now is like, Hermes, you're not talking about Hermes. I still use Hermes a ton. Hermes is still a fantastic tool.

It is the only usable open source AI agent I think right now. It is excellent. So you want to use it for the strengths that you get out of an open source AI agent, which is one, you can use any number of models and two, you can customize it any way you want.

So if I'm doing network administrator stuff, which is loading local models, my different computers, managing my tech, managing all my different computers, I like to use Hermes for that because Hermes is a lot more willing to jump between my computers. There's a lot of guardrails on the other AI agents when it comes to that.

Also for personal work, for the crunch. jobs, for doing things that might require or be better with multiple models. I like Hermes.

For the deep technical work, I like Chad GBT work only because that harness, that desktop harness is excellent. The computer use in that is Just the best, bar none, the absolute best.

So I like chat GPT work for that. In more general knowledge work, I like Grokbot because I think the Grokbot interface is excellent. I think it's super easy to use.

And also it has the mobile app. Hermes still doesn't have a mobile app, which is, that's a big weakness. Grokbot has the mobile app.

So for quick general knowledge work, I like to go to my Grokbot app on my phone, shoot off some commands real quick, and I get a lot of work done. That's my stack. I'm still using Hermes.

It still manages all my computers for me. love the iMessage integration so I can go to iMessage and quickly shoot off prompts as well. That's what it's great for too.

But you want to mix and match. You want to use the different agents and use it for each of their strengths. I hope this was helpful.

If it was, leave a like down below. Let me know in the comments which AI agent you use the most. Hermes, Grokbot, Work, OpenClaw, whatever you use the most.

Let me know down below. I'm curious. I'll start making more videos about whichever agents you guys like.

Subscribe and turn on notifications. All I do is cover all the AI agents, how to use them, how to get them. most out of them.

I hope this is helpful. I'm so appreciative you'd watch this video and I'll see you in the next one.

The Hook

The bait, then the rug-pull.

Hermes just shipped ten updates worth restructuring a setup around, and the video's real argument is sharper than a feature list: stop building bots by job role like Grok encourages, and start building one bot per model instead.

Frameworks

Named ideas worth stealing.

12:11list

My Stack

Deep technical work: ChatGPT Work
General knowledge work: Grok Bot
Network administrator / personal work: Hermes

The creator's own three-way split of which AI agent handles which category of task, based on each tool's strongest interface (ChatGPT's desktop computer-use harness, Grok's mobile app, Hermes's willingness to operate across multiple machines).

Steal fordeciding which AI agent to open by default for a given task instead of defaulting to one tool for everything

CTA Breakdown