← Back to search

Hermes Voice Agent is INSANE!

AI News Today | Julian Goldie Podcast · 2026-07-04 · 7 min
relevance 44 1563 words Episode page ↗ Audio ↗
Show full episode description
Meet Hermes Apollo: A Local, Voice-Activated Jarvis Inside Agent OS (Build Apps, Briefings & Browser Control) The script demonstrates Hermes Apollo, a voice-activated assistant inside Agent OS that responds quickly via ChatGPT real-time and can run agentic tasks through a backend agent using GLM 5.2. The presenter shows Apollo telling a joke, teaching a Chinese word (“xie xie”), building a snake game and a 24-hour countdown timer with previews, and opening a website by voice. Apollo supports wake-word hands-free use, wall mode, chat and build history, weekly/monthly briefings, memory recall via an Obsidian “memory galaxy,” and can switch to agent mode to control the browser. The broader system includes Hermes Oracle for trending Twitter news and Hermes Astros for competitor monitoring and content idea generation. The presenter emphasizes speed, usefulness beyond Siri, local/private operation options, and invites viewers to get the full setup in the AI Profit Boardroom with tutorials, guides, coaching calls, and community support.
✨ Episode Outline — click any point to jump to it in the episode
Problem solved
Adds a hands-free, Jarvis-style voice agent (Apollo) on top of Hermes Agent OS to build apps, run briefings, and control the browser by voice.
Benefits
  • Wake-word, hands-free voice control on Windows or Mac
  • Fast replies via ChatGPT realtime with GLM 5.2 backend
  • Recalls memories from local Obsidian vault
  • Switch between quick answers and agentic mode
  • Runs locally for privacy on local models
Use cases
  • Voice-built a snake game and a 24-hour countdown timer
  • Opened juliangoldie.com hands-free via agent browser control
  • Ran daily/weekly/monthly morning briefings with action items
  • Generated SEO and social content via Hermes Oracle from Twitter trends
  • Hermes Astros monitors competitor watch list for content ideas
KPIs / results
  • 194 pages of testimonials and wins
  • Apps built in the last 30, 26, 21 and 7 minutes
Tools / build
0:00 / 0:00
📑 Chapters — tap a time to jump there
00:00
Meet Apollo Demo
  • Apollo greets user and tells a quick joke
00:28
Voice Commands Build Apps
  • Voice commands build a snake game and countdown timer
01:00
Jarvis Style Overview
  • Jarvis-style voice agent plugged into Hermes Agent
01:33
Briefings And History
  • Morning briefs with suggested focus and action items
  • Views daily briefing history
02:17
How It Works Backend
  • ChatGPT realtime for speed, GLM 5.2 as agent backend
02:51
Modes And Wake Word
  • Warm mode, full screen, wake-word listening
03:18
Agent Mode Browser Control
  • Agent mode can control the browser for you
03:51
Prompts And Use Cases
  • Example prompts: maths, marketing, Kanban, disk space
04:15
Memory With Obsidian
  • Recalls memories from local Obsidian vault
04:38
Oracle And Astros Tools
05:43
Not Just A Toy
  • Not a toy: reads memories, builds and creates
06:03
Privacy And Local Models
  • Runs on local models; memories stay local
06:18
Setup Proof And Testimonials
  • 194 pages of testimonials prove easy setup
06:34
Get Agent OS Access
  • Get Agent OS with Apollo in AI Profit Boardroom
07:02
Community Coaching And Wrap
  • Weekly coaching calls and local community meetups
Apollo, how are you today, sir? Apollo, impeccably well, sir, and ever ready to assist you. And how are you feeling today? Yeah, I'm doing great, I'm doing great. Can you just tell me a quick joke, mate? Apollo, certainly, sir. Why did the Scarecrow get a promotion? Because he was outstanding in his field. What's a good word to learn in Chinese? A splendid word to start with might be 谢谢, which means thank you. Always useful and ever so polite. Could you build out a snake game? Building that now, sir. The snake game is ready for you, sir. Enjoy. Could you build down a countdown timer for 24 hours? Building that now, sir. And then once that's completed, we'll actually get the preview as well down here. So you can see a bunch of stuff that's built out recently for me, like, for example, 30 minutes ago, 26 minutes ago, 21 minutes ago, seven minutes ago, etc. This is a pretty powerful system that we're using here with Hermes Apollo as a voice activated agent. It's basically like a modern day Jarvis plugged into Hermes Agent. Now, if you're wondering, OK, how does it work step by step? Let me guide you through it. So basically, you say the word and then you can run this on Windows or Mac. You don't have to just use Mac. And it's basically like a voice copilot inside Agent OS. So I can say the wake word and have the wake word switched on and it can answer. So it can run agentic tasks. It remembers what you tell it reads a morning brief as well. So we can click on the briefing section here and it can actually run briefs for us and we can see our history as well. So we can see previous histories from the past as well in terms of daily briefings. And then it will just pull that up in the background whilst I'm talking to you, which is pretty amazing stuff. So you can see here that it's got the suggested focus, how many action items are opening and the open Saturday, sir. Your notes suggest a diligent tidying pass. I'm just going to mute that, but you get the point. Pretty powerful stuff. And then we can see our previous briefings. We can see what worked on, you know, what's on our mind. What are the main headlines this week as well, which is pretty cool. And the way this runs is basically we have chat GPT real time. That's why it's so fast to reply. And then we have Jarvis connected on the back end as an agent. And I'm using GLM 5.2, but you could use whatever you want. I think the GLM 5.2 is a good balance between speed and actually getting really nice outputs from it as well. And you can see when it's speaking, it glows up a different color. And also if it's really not a briefing like it just did a second ago, then that'll be quite different to the color that would use when it's responding to you. So you know what it's doing, etc. So it's pretty powerful stuff what it can do. And you might also wonder, okay, how can you use this? Well, I can say Apollo from across the room and it's listening. It can be in warm mode so we can have it full screen as well, running whenever we need it. We can see our previous history over here, which is pretty cool. We can switch between weekly and monthly briefings as well. And it could just reread the briefs to me. And it's running locally as well. So it's got a wake word. It's hands-free. It hears you. It does speech to text. It has a brain, so it runs with GLM 5.2. Or you can switch to agent mode as well. So you can actually switch over here to agent mode. And this can also control your browser and that sort of thing as well for you. So, for example, if we go back to normal mode here and we switch on real time again, can you just open up juliangoldie.com? And then it just does it like so. It's pretty insane. So it's really, really fast to respond. Very agentic. And you can see the previous history as well of your chats as well, which is great. Plus, you've got everything that you've built over here too, which is really, really useful. I haven't seen anyone else create something like this. It's just available. We give it away inside our agent OS. You could build it from scratch. But if you want our setups inside the profit boardroom. And here's some example prompts that you could run. So you could ask it like, okay, you know, for maths, you could ask it for marketing ideas. You could ask it to open like your Kanban board up or that sort of thing. You could even ask it like how much disk space you have left or what are the biggest files in your downloads folder, all sorts of different things. So you could use it for remembering things as well. So it's actually plugged into our memory galaxy inside Obsidian. The great thing about that is it can recall memories. And also when we use it, like you see, it was just updated two minutes ago. It will actually recall the memories that I give it as well. And then we can use it for content creation, for building things as well. You might notice before that actually gives a preview of what it's built. And this is all working alongside everything else that we have inside the system. So we have Hermes Oracle that can put in the latest trending news from Twitter. And then we can create SEO content and social media content based on that. Plus they updated with the latest headlines. And we also have Hermes Astros. And Hermes Astros, basically what it does is it looks at your competitors. And you can change your watch list as well. So we can have competitors that we're monitoring. And then we can come up with new content ideas that are inspired by the original competitor. And you can change the watch list. It's super easy to use. It can generate ideas on tap. It gives you the angles relevant to you. And the other cool thing about this is I could generate SEO content. Or I could generate a video of that. Or I could actually plug it into Notebook 11 as well. So there's like three different ways I can use that content to come up with ideas quickly. And so Apollo alongside all this stuff is crazy powerful. We can also describe an app. Just watch it appear. We can ask it to remember stuff. We can have a live conversation. We can choose between quick answers or agentic answers depending on how fast you want it to be. And it can wake up on a wake word as well. Now you also might say, okay, well, voice assistants, they're just toys. But actually, you know, this is not Siri. This is something that can genuinely look at your memories, build something, create something. As you can see right here, it can look at your memories and give you a weekly brief. It's ready to go whenever you want. And it works super fast. It's faster than, for example, something like Siri. So it's a really powerful tool. Other people say, well, talking to an AI about my business, maybe that's not private, etc. But you can run this on local models if you wanted to. Bear in mind the memories and everything else and all the chat here. It's running locally on my machine. It's just plugged locally into my Obsidian Vault. And then you also might say, well, setting up a voice assistant, that must be difficult. But actually, we've got 194 pages of testimonials and wins, many of them using the AgentOS system that we've set up. So we've got 194 pages. And you can see some of the wins and testimonials here from people absolutely crushing it with this stuff. So if you want to get our full setup, you can get that inside the AI Profit Boardroom. Link in the comments description or go to the AI Profit Boardroom. Inside this community, you'll learn how to save time, grow and scale with AI automation. Plus, you get the full system from me. If you want the AgentOS with Hermes Apollo plugged in, you can get that right here. So we've got the AgentOS system. You can get the video tutorial, the last update date. You can get the zip file as well with a full step-by-step tutorial. And then also, we've got new daily guides based on what's actually useful that's just dropped. And inside the community, I actually personally create a video tutorial and reply to everyone inside the community. And then also, you can jump on the weekly coaching calls inside the calendar. And you can meet people locally near you who are building with AI agents like Hermes and the AgentOS. So feel free to get that. Link in the comments description or go to the AI Profit Boardroom.com to get access. Thanks for watching.