OpenClaw vs Hermes: Who Wins?

So today we're going to be comparing OpenClaw versus Hermes to see who wins and what the differences are. Now this is based on a question I got inside the AI Profit Boardroom. So Sophia was asking about OpenClaw, what's the difference? I think a lot of people are confused, which one is the best to use and also what makes some difference?

Why are they similar? What tasks are they best for, right? So basically to, to summarize quickly, what I've found is that Hermes is a lot smoother and easier to use and that OpenClaw tends to break a lot more. The other thing that I've found is that because Hermes was engineered by one of the biggest AI labs in the world, News Research, because of that, they've basically created something that evolves over time.

It gets better and better, right? Whereas, for example, if you look at OpenClaw, it's become worse over time. Let me show you an example right here. So if we go over to OpenRouter and you can see the general consensus.

So you can see how these agents are performing. If you look at the most popular agents in the world, Hermes and OpenClaw are right at the top on OpenRouter. OpenRouter is a place where people use APIs. So you can get a feel for what is being used the most.

Now this year, Hermes launched in February. So it's newer than OpenClaw and Hermes has actually gradually overtaken OpenClaw directly. So for example, if you look here, you can see that the trajectory of Hermes is that more and more people are using it over time. The graph is going up.

The trend is going up. If you have a look at OpenClaw, it has declined like over the last, this is only the last 30 days, but I've seen it drop in really since the release of Hermes and that's because it's just a much smoother experience. Now, when you're using them side by side, recently I have noticed that the OpenClaw has become smoother to use. It's less buggy.

It breaks less, but I tend to find myself using Hermes more and more. And also they're releasing some interesting stuff that's actually useful. So for example, OpenClaw, they've released a bunch of interesting features recently inside their releases, right? So for example, they have brought out stuff like being able to talk to your agent inside Google chat or Google meet.

They've actually got an app out as well, but I think most people are not using this stuff, right? The main use case that I see for using AI agents is that you have them working as a team. You're doing some work on your laptop and you can start using OpenClaw or Hermes directly on your laptop. Whereas for example, I don't know many people actually use OpenClaw inside Discord or Slack.

It tends to be like, they want to go to one centralized hub where all of their agents are living together, like Clawed and OverClawed, like we've got inside this agentic OS system right here. Now, when we actually look at these systems as well, they're very similar in terms of the models they can use. So if you actually look at what are the most popular models that people use inside Hermes, you can see the top three right here. And if you have a look at OpenClaw, it's similar, right?

It's not far off at all. Now they pretty much have similar functionality in terms of the models they can use. They can both use free APIs as well. So they can both use stuff like our Alpha as well, which is a free API on UberRouter.

And also one big difference between them all is that Hermes, I've seen they've organized their knowledge a lot better. So let me show you an example of that. If we go to their news research portal here, you can see that they've organized their knowledge better. Whereas for example, if you want to get the same thing for OpenClaw and the documentation on OpenClaw, they do have an OpenClaw docs set up here, but it's just, it doesn't feel as easy to navigate around.

It's not as useful as I find myself coming back to Hermes agent and learning new things all the time. So you can see, for example, they have a Kanban set up, which you can't get with OpenClaw. They have the persistent goal set up, which is their take on Ralph Loop, which is a way of just using agents autonomously as well. So there's some feature differences too, in terms of Kanban boards, persistent goals, they've added MCP catalogs as well.

Some interesting features that I don't see anywhere else. And also when I look at what OpenClaw is releasing versus Hermes agent, I feel like Hermes agent is actually listening to what people want and paying a lot more attention to what are the problems and then how can they solve them? Let me give you another example. So today they actually released something called Hermes desktop, right?

Hermes desktop. It's a free application that you can use and you can plug your Hermes agent too. Now, why did they do that? They did it because there was no gateway for Hermes agent previously.

You couldn't really chat to it unless you create your own agent operating system. As they knew that if they wanted to keep growing beyond the current trajectory of where they're at, they had to release something that was user friendly and easy to use rather than the terminal, right? Like how many people are just going to open up the terminal and then start coding, essentially coding inside a terminal command line inference like this. You're not going to do that, right?

So that's why they've released Hermes desktop. You don't really see that for OpenClaw so much. You don't really see them looking and paying attention. I see a lot of the releases, they sometimes they bring out shiny objects or flashy features, but these are features that 99% of people are not going to use.

And the honest answer as well is I would say you probably want to use both, right? So Hermes and OpenClaw, it's good to understand both if you have the time, because also you can combine them, right? You can have, for example, Hermes fix things inside OpenClaw. You have OpenClaw fix things inside Hermes.

And sometimes you're going to need that between all of them. I regularly get clawed, for example, to fix both of those. Now, in terms of these specific questions, so we've got some great questions from Sophia here. Number one is primarily if you'd like to automate some daily and weekly routines related to work in a way where you don't need to trigger them.

You can do that with either Hermes or OpenClaw. Now, if you've never used both and you're like, okay, which one, which direction do I go in, I would just go with Hermes. And the reason I say that is it's smoother and easier to use, it's more user-friendly and it's more beginner-friendly. So that's why you want to go with Hermes.

So either of them could do it, but stick with Hermes. If you're wondering how to do it, you just go into Hermes and you say each week, go off and do this, just give it a schedule of tasks. That's pretty much it. Now, the next one was you want to, for example, check post messages to WhatsApp and Telegram.

Again, you can use both. So you could use OpenClaw for this, or you could use Hermes. Which one would I personally pick? I would go with Hermes.

Why would I pick Hermes? Because it's smoother again, right? So you can see the current trend here. And then finally keeping track of stuff like this.

This is an interesting one. So the way that I would actually do that is I wouldn't use Hermes or OpenClaw specifically to store information or data. And the reason for that is because agents straight out of the box, not that great with memory, not that great at remembering things. It's kind of like, I would look at Hermes's hands, which is the hands go off and do things.

Then I would look at, for example, the brain that you plug into your Hermes agent, which is the API. I would look at that. For example, we've got minimax here. I would look at that as the brain, right?

So you got Hermes agent, which is the hands. You've got the brain, which is minimax or whatever API you want to plug into that. And then finally, you've got the memory and the memory. I would actually use Obsidian for this instead, right?

Obsidian is a lot more powerful and you can see an example right here. So this is great for storing information. And you can say to Hermes, connect to my local Obsidian vault. And then every time I use it, make sure that you write the conversations and you store the conversations inside the Obsidian vault.

And so that's a powerful way to just store a memory inside your AI agents to keep track of stuff. So for automating weekly routines, Hermes, for checking and posting messages, Hermes, for keeping track of information and data, and then using that as context and also automating the note taking and the actual context storage, then you want to use Obsidian. So you can see, for example, here, we have a knowledge graph plugged in. And the great thing about that as well, it's not just that it plugs into Hermes or into OpenCore, but it goes into all of your AI agents, which means that your AI agents can all sync together.

So if you have, for example, a list of data or a set of data in one agent, that's automatically transferred to other agents because you link them all to your Obsidian memory, which is just like a free note taking app locally. It's like literally all it is just a bunch of miles down files collated together and as beautiful as the knowledge graph looks, that's basically what it's doing, right? It's just organizing things together, keeping a list of projects and files and folders so that your AI agents can write to them and also pull them into memories as you can see right here. Now, if I was to create something like you were talking about, Sophia, then what I would actually do here is I would actually list that inside Obsidian as a new markdown file, and then say to Hermes, connect to my local Obsidian folder, particularly this one folder here.

And also if I make any changes or you notice I make any changes, please update that too. And that's the way that I would do it. The other cool thing about this one is we usually use something called OMI. And OMI, what it can do is it can take notes on you automatically whilst you're working, it looks at what you're doing, it listens to what you're doing, and then it writes it automatically to your Obsidian vault, and that's pretty powerful as well, because then again, you're not managing this automatically.

Imagine how long I would have to take to sit down and connect all this stuff together, it'd be very difficult, very time consuming, whereas, for example, if we got our AI agents to handle it for us, no problem, right? So that's all three questions answered. Really powerful stuff. I've heard these agents you can't go wrong with, but if you want to stay focused, you don't want to feel overwhelmed, then go with Hermes agent.

The other thing I've noticed is it's just a lot more interest in Hermes agent in general, and I think that's because it is such a powerful tool versus Overclaw. I don't hear that many people talking about it. Final thing that I would say is that Overclaw were the kind of original AI agent to bring out such an autonomous idea, right? The idea of an AI agent that can schedule tasks and everything like that.

So I think basically what's happened is Hermes have looked at the best things that Overclaw does and all the worst things, and then tried to fix each one of them and then build into their system in a smoother way. Final thing that I would say between them is the Hermes actually has new support behind it, which means that you can plug in free models into Hermes agent that you couldn't do with Overclaw. So for example, what you can actually do is you can switch between models here. If we go to Hermes model inside the terminal and we want to switch the model and then we can select news portal and news portal, even if you're on the free plan, it allows you to use free APIs inside the terminal.

So if you go and we have a look at what we've got available, you can see that we can actually select step 3.7 flash for free, and we can use that free model. And it's available for free for, I think another, at least another three weeks. So that's pretty cool as well. That's another benefit that you don't get inside Overclaw.

So thanks so much for watching. And if you want more details on the Obsidian setup with OMI, we've got something that we call the infinite context engine, and we've got a full video tutorial on that, plus a game plan in terms of how to automate it and how to implement it. And also, if you want to get my agent operating system that helps you manage these AI agents in a really powerful, but easy way, you can get that inside the AI platform as well. We've got a zip file here that you can use and install.

We've got the full plan as well. And then we update this daily as well. So you can ask questions inside the community. I answer them with video tutorials like I did today.

You get all of my new trainings inside the classroom. You get all my new lessons. We update this daily too. You get the new agent operating system, weekly coaching course as well.

And that's all inside the AI Profitable Boarding. Link in the description or just go to the AIprofitableboarding.com. Thanks for watching.