Hermes Agent is officially the best AI agent ever made. They just released an update that has several new features that completely change how I use Hermes Agent. In this video, I’ll cover the seven new features you need to implement into your workflow today, plus towards the end, show you how you should be using Fable 5 with your Hermes Agent. This is a mustwatch. This is a banger. Now, let’s lock in and get into it. All right, I’m starting off with one of the best features ever implemented into Hermes agent and that is mixture of agents. What is mixture of agents? Well, let me show you. When you type slash MA and then you put in a prompt after it is going to initiate the mixture of agents. Now, what is mixture of agents? Well, what’s going to happen is my aggregator model, which is my orchestrator, is going to take that prompt. So, that’s whatever the model you’re currently using. For me, that’s Opus 48. It’s going to take that prompt and it’s going to send it to a bunch of reference models, right? So, we’re taking this prompt. It’s setting it to a bunch of reference models. These reference models by default are chat GBT as well as deepseek v4 through open router. That’s the kind of the default way they do it. It takes the prompt, gives it to all these reference models. The reference models answer the question and then give the response back to the aggregator model which again opus 48. The aggregator model takes all their responses and then synthesizes it into one response. One synthesized answer according to new researches benchmarks. This results in a much better higher quality response. They tested all the models. They tested a bunch of different reference models. their best combination of models was again Chad GBT and DeepSeek and that is kind of the default in here. All right, so all you need to do to make the mixture of agents works is click on the dropown, choose MOA default. That’s going to send it both to chat GPT as well as DeepSeek 4 through open router. I’m going to give it a prompt based on what you know about me and my interests, passions, goals, and ambitions. What are five SAS ideas I can build out today to make money online? That’s a prompt you can steal right now. Feel free to steal that. Use that with your mixture of agents. Hit enter. Now all the agents are going to get together, convene, chat with each other, figure out what are the best five SAS ideas based on all the conversations, all the memories it has about me and give me a really nice synthesized list of ideas I can start building out immediately. So if I want to turn around after this, go to Hermes and say, “Hey, build that idea out. I really like that a lot.” It can do that. So Chad GBT is talking. Deep See, Deep Seat’s talking. Chad GBT. They’re coming up with different ideas. And here’s a nice synthesized answer right here. And boom, here’s an actually a bunch of awesome really, really good ideas for SAS. I can take one, start building out now, and boom, I have a weekend project for myself. Do the same thing. Set up mixture of agents. If it doesn’t work for you off the rip, it’s probably because you do not have open router set up. Open router is default. The second model uses the default first models, chat GBT. If it’s not working, make sure you have those API keys in. Ask Hermes. It’ll set up for you. Really, really easy to do. mixture of agents. Awesome new feature to get even better answers out of your Hermes agent. The way I’d use this is just whenever you have kind of more complex questions that can go many different ways. I use the mixture of agents for it. Makes it really nice to use. The next major feature in this release is slasharn. This is an amazing way to teach your agent new skills. Basically, the way it works is you can hand your agent any URL, any prompt or run slasharn after any task, and it will automatically create new skills and memories around what you gave it. Let me give you a good example here. So, if you’re anything like me, you’re on X all day. You see tweets with cool tips on how to use your agent, how to use Claude code or whatever, and oh, I’m going to go recreate that in my Hermes. Now, what you can do is take those tweets and just do slasharn and have your Hermes make a skill based on every tweet you see that’s helpful. I got this tweet here by me. Great tweet on coding loops. I’m just going to take the URL for this tweet. I’m going to go to my Hermes agent. I’m going to do new session. I’m going to do slasharn paste in the URL and I’m going to hit enter. And what’s going to happen is the agent’s going to go read the tweet and then turn it into a skill. Now instead of having to explain every single thing you see online, trying to make skills out of it manually for your agent, you just give it a URL, do slasharn, and boom, you have a brand new skill automatically made. Slasharn is the quickest, easiest way to turn anything into new skills automatically. Anytime you think of a new process, anytime you see a helpful tweet or article online, you just do slasharn and then type it in after. You can even do it where if you have your agent do a whole long process, you’re doing something, you have it build something, you’re like, “That worked out great. I want that to be a repeatable skill, you just do slasharn and hit enter, and it’ll take everything from before that and turn it into a skill.” It is a really good way to quickly self-improve your age. And as you can see here, boom, new skill just made based on that one tweet. Every time I see an interesting tweet, I do slash learn, put the tweet in after, and it’s good to go. Slasharn, use the hell out of it. This next one is an awesome one that builds off of slasharn, and it is slashjourney. This is a great way to see everything your agent has learned and all the skills and memories it has. Look at this awesome chart. Now you can see every memory, every skill made from all of your conversations you’ve ever had with your Hermes agent. And you can see how they’re all connected. You can see how all the skills connect to all the different memories. I started building a game. It showed me all the memories attached to building games. Here’s my work around building local models and putting them on my computer. You can see all the memories around local models. Really sick way to see what your agent has learned about you as you’ve worked with it slashjourney. You can see this amazing chart and just a good way to make sure your agent is learning along the way and all the self-improvement it’s had. Which brings us to the fourth improvement of this new update, which is self-improvement got cheaper. Now, every time your agent learns something, every time you do slasharn, every time it self-improves automatically, it actually automatically switches to cheaper models to implement those learnings. A big part of the cost with Hermes aging is there’s a lot of complaints about cost, especially if you’re using anthropic models is it’s really expensive. Well, the issue is is a lot of the things that happen in the background. Creating memories, creating skills, learning new things, those are very expensive tasks and it uses your Opus model, if that’s what you’re using, your Chad GBT model to do those things. Now, it’s actually delegating those tasks to cheaper models in order to save a lot of money. So, if you’re using Hermes Agent regularly, you should start seeing much better cost savings as you go along. Major update, really awesome to see. Next up is massive improvements to vibe coding. Now, when you vibe code inside Hermes desktop, you have full git controls. You can see code. You can see diffs. You can make commits. You can open up pull requests. It’s all built into Hermes. Now, this is an actual viable vibe coding tool. If you look here, I asked to build a 3GS game, which for the record, I’m going to show you the game in a second. I actually built is incredible. Probably the best 3GS game I’ve ever seen built out of this. But what you can see here is it creates all the files. You can see all the diffs. You can see all the code changes. And if we go over here to the right, you can actually make commits and actually open up pull requests straight from Hermes. So, this is a viable vibe coding tool if you want. You don’t need to use claw code anymore. You can use this and just build out your code and your apps straight from Hermes. And Hermes is a very good vibe coding tool. Check this out. I just asked to build an action RPG like Diablo and this is what it came up with. This is actually really, really nice. You can see the graphics are good. You can see the hit counters. You can see the spells it gave me. It has full levels. It has leveling up. This is really amazing. This is a really good game that Hermes vibecoded all by itself. This is probably the most impressive uh vibecoded 3GS game I’ve ever seen. This was Opus 48. I’m getting really into Path of Exile 2. So, this is uh certainly holding me over. If I am you, I try Vibe Coding now inside Hermes Agent. Especially if you have like your Chad GBT subscription plugged in. So, you’re so you get all those free credits with your subscription. I think you get get away with using this as your vibe coding tool now because you can see the diffs, you can create pull requests, all of that. Really, really nicely done. This desktop app is incredible. I mean, this is probably the sole reason Hermes is ahead of OpenClaw right now. So, take advantage of it. Test it out. Do some vibe coding in Hermes. I’m really, really impressed. And the last bonus recommendation I want to give you here is around Fable 5. Fable 5 is now available in Hermes Agent. As you can see here, they have Fable 5. Here is my recommendation on how to handle this. I would go in, start a new session, and ask your agent to create a new Hermes profile specifically for Fable 5. So, here’s the prompt I would use. Please make a new Hermes profile called Oracle that uses Fable 5 model from Claude. Let me know when that’s set up so I can use it in Telegram. For those who don’t know, profiles in Hermes are basically new Hermes agents. So, every profile you set up is a new Hermes agent you can use. I highly recommend setting up a new Hermes profile built specifically for the Fable 5 model. And I’m not using this as the daily driver. Not at all. You do not want to use as daily driver. It is way too expensive for that. But what I’d use it for is super super super complex problems. Right? You have your mixture of agents option which is one way to handle complex problems that I think is more for like complex questions and getting really wellthoughtout answers. What I like to use Fable 5 for is when I’m building things with Hermes agent. Hey, build this out for me, build out for me. I find coding with Fable is significantly better even when you use Mixture of agents. Mixture of agents is good when you need opinions from multiple models to get a nice synthesized answer. Fable is good when you want like a perfectly built out front end, a perfectly built whatever, Fable 5 will do that the best. So, I highly recommend or if you’re doing really complex actions across your computers, like if you want to set up a local model on your DJX Spark that connects to your Mac Studio that does this on another computer, really complex tasks that are multi-step across different devices, I would use Fable Agent for that as well. So your line of thinking is complex questions, use mixture of agents, complex tasks, use your fable agent. You set that up by setting up a new profile inside Hermes and it will go and build that out for you. Then you can set it up in Telegram and you’re good to go. You can go on your Telegram and talk to that agent at any time. Just as a side note, I’m going to do a full boot camp on Hermes agents. We have multiple full boot camps on Hermes agent inside the Vibe Coding Academy. Link for that is down below. It’s the number one community on AI on the entire internet. I promise you will not regret joining. Build alongside a thousand people doing cool stuff with AI. You’ll learn a ton of stuff. Promise it’ll be worth it. Link down below for that. You learned anything at all, leave a like down below. Let me know what you want in the next video. More Hermes agents tips, more Fable 5 tips, more Claude Code tips. Let me know down below. All my videos are based on your feedback. I hope this was helpful. Make sure to turn on notifications so you do not miss the next video. I will see you in the next