OmniRoute: Run AI FREE Forever!

Today I want to show you a powerful new tool that means you never have to pay for AI again. And this is a really interesting, new, free, open-source project that can work across all of your favourite coding tools. It's called OmniRoot, and what it means essentially is that you can use it in any way you want, whether that's directly with your tools, whether that's, for example, inside your agent operating system. You can build whatever you want.

And then also, when you're doing this, you never have to pay for AI again. And I'll show you why in a second, but let's just demo it out right here. So, for example, if we say, okay, create a galaxy-themed website with amazing animations on a simple landing page that looks super dope, meaning juicing and fun, right? It's just something basic like that.

So you quickly type in the prompt here, as you can see, or you can use WhisperFlow, whatever you prefer. And then what you're going to see is that you get the prompt here. Then you're going to see that it starts rooting through free providers. You can see what you've saved, so what you've previously created down here, and then you can see the preview of everything you've built and the code over here.

And you can save and download this whenever you want. So it's a really powerful tool where you can code for free, preview it, save it for later, customise it however you want, and it's free. In fact, this means that you never need to stop coding again. So, you know, if you're worried about tokens, if you're worried about using agentic tools, if you're worried about, like, your builds just adding up for APIs, I don't see why you wouldn't use this.

It's pretty unbelievable. And so the way that it works is basically you connect every AI tool to 237 providers, and over 90 of them are actually free through one single endpoint. Now, you could use this agentically as well because you can use custom endpoints with something like Hermes and then plug in free APIs into Hermes as well. Now you can see that we get the code back directly over here, directly from our setup, which is pretty cool.

And if you want to see some stuff we've already built previously, you can see an example right here. We built our animated keyboard. We created, for example, a to-do list app and also a Galaxy background, as you can see. And then if we want to see the code, we've got that over here.

If we want to save it, we can save it for later, and we can open that up in a new tab as well. Pretty amazing stuff. Now, also what's really interesting about this is it uses two token minimization playbooks. So number one is RTK, and number two is Caveman.

So what that means, essentially, is that when you're coding with either of these tools, you save 15 to 95% of your tokens, which means that you're never having to worry about rate limits. Because let's say, for example, you've got one endpoint, so you don't need to configure anything, really, once you've set it up. Then you have 93 tools that it runs through, and they connect all to one endpoint. You can plug it into Cloud Code.

So Cloud Code, Codex, Cursor, Client, all these can be used for free as well. And it's got auto fallback. So what that means is if one of these 90 fails, no problem, you can plug it into another one. Let's just try something else out now.

So I'm going to say, OK, create a habit tracker app, like so. And whilst we're waiting for that, what that means is because you're rooting through so many different APIs, and you're limiting the number of tokens you use, you're not going to hit rate limits, so you're not going to be kicked off using that particular tool. Usually, for example, if you're using free APIs or free tools, you can get rate limited very quickly, which means that you've run out of tokens, and your tools just stop working. You're like, ah, it was free, but it doesn't work.

That has often happened to me in the past. And it's not like I'm a miser or anything like that. Like, I really love using Cloud. We use Fable, Fable 5 all the time.

I mean, I actually have my own benchmark website where I test 45 different projects across all of my favorite models. And you can see an example of that right here. You know, for example, like with Fusion, and we create amazing stuff, right? I'm more than happy to pay and try different things.

But my point is that if you're worried about free APIs, which I know loads of people are, then you can use something like this to help you. That's what we want. I think that's fantastic, because it means that AI is free for everyone. Also, this is open source, so it's available on MIT license, which is great.

And then the promises here are that you never hit limits. You save up to 95% of tokens. It's free to start. There's a free tier.

And there's 11 free forever options as well. Every tool actually works, so all the coding agents work as well. You get one endpoint, and then it's production grade as well. It actually works.

I mean, literally in about 30 minutes, I plugged it into my agent operating system. We have a free coding tool here. I mean, I could switch to Fusion or some more of the expensive tools if I want, but I've got the free version here. I can preview everything, also fall back 90 different free products.

We can download it. We can copy it. We can test if it works. And it actually does, which is fantastic.

So we can say, okay, we want it for that day, et cetera. And then we can save builds as well. And that will save to my workspace. The reason that you want to save builds is like, if you use this tool and you just build stuff, but you don't have a good system for saving it like we do, we have a good system here for saving it, you'll just lose it.

I know that because I've been testing AI for ages. So that's why we have that. Also, we'll say that I've tested local models a lot. For example, like we were testing agents A1 this morning, and we have a local benchmark leaderboard.

Nothing comes close, really. Even, for example, Quable 5, I would say, is nowhere near the same level as this sort of stuff. So Quable 5, you can build some okay things, but it's never going to be the same quality with local models as it is with these frontier models you can use on free APIs. So if I have a choice between using something like OmniRoot or using free local models, unless I really need to do something private, which is basically never, then I would just stick with the OmniRoot.

I think that's probably the easiest way. And also, you might be wondering, okay, what other problems to solve? What other use cases you have, et cetera? Well, when you think about it, right, the old way is like you have a subscription for all your different tools, one for Claude, one for Curse, one for Copilot.

The free tier runs dry. You're locked out mid-build. One provider goes down, your whole day goes down. Switching models means you have to rewire every tool from scratch, which is just really annoying in itself, and then you pay per token to keep your agents typing.

With this setup, you set it up in like five minutes. Every tool points at one single local URL. You get 90 free providers built in. If a quota runs out, it roots to the next automatically, and you don't even notice.

And then you can set up model auto to pick the best available model and swap anytime with no rewriting. And you stop paying per token because the free pool basically runs your day. It's like a pool of different APIs working together. And also, the keys are encrypted locally, so the prompts never leave your Mac.

You don't have to worry about an API key. How nice is that? And the way this works is you ask, Omniroot picks and falls over. It switches between 90 free providers, and you just keep building, which is really, really cool.

I was actually looking for something like this the other day, and it wasn't out, and it's just dropped, really. Also, some people say, well, I'm not technical. I don't like this technical terminal stuff. But it's literally like one command.

It's one prompt to set this up. So if you want to set it up, you just use one command to spin up the gateway like this, and then you export it like this if you want to use, for example, like Cloud Code inside it. And then the way it's going to work is there's one endpoint, and that just maps out to all the free providers that are actually available. It's pretty cool.

Also, some people say, well, free AI is no good, but you've seen the outputs. Like, it's pretty good. Is it as good as Cloud Fable 5? No.

Is anything? No. So, I mean, the other thing that people say, well, setting this up is a technical rabbit hole. I'll never finish.

Well, actually, if you want our setup, so we've got this agent operating system, as I've shown you before. If you want our setup, that's available inside the AI Profitable Boardroom. So if you just, like, want this ready to go, and you just want a system that has everything built in like we've got, then you can get that inside the AI Profitable Boardroom. Link in the comments description for our agent operating system.

And also, some people say, well, wait until the free AI thing settles down. It won't. This is only speeding up. Get involved now.

Start learning now. Otherwise, you're going to fall behind. So that is it. That's my take.

Now, if you want to get the full system with the OmniRoot free coder, the local Hermes engine, Agent Kanban, the Cloud workspace, every CLI plugged in, free local models, the AI mastermind with a group chat of AI agents, and 3,900 founders and me, you can get that inside the AI Profitable Boardroom. We have this full system with OmniRoot, the free local engine. We've got, for example, Cloud, Hermes built in, et cetera. We have a full memory system that you can plug into this.

And also, with Hermes, we build out loads of cool custom workflows, like Apollo Voice Agent, Hermes Oracle, Hermes Astros, whatever you want to use to build and automate whatever you want. And if you want to get all of that, it's inside the AI Profitable Boardroom. Link in the comments description or go to the AIProfitableBoardroom.com. Inside the map, you can actually connect with people locally near you who are building with AI agents.

Inside the classroom, if you're on that agent operating system I showed you a second ago with OmniRoot, we've got that over here. And we have a full step-by-step tutorial on how to use OmniRoot as well. And with the agent OS, we update it daily so you can see when it was last updated. You get the video tutorial, plus you get a zip file to install it.

And you also get new daily tutorials based on what's just dropped. Now, inside the community, you can ask questions, get help and support in real time. And inside the calendar, you can jump a weekly coaching calls. We actually have four of them per week.

So I hope to see you inside there. Link in the comments description or just go to the AIProfitableBoardroom.com. Cheers for watching. Ba-da!