Codex is FREE Forever, Here Is How...

Codex is free forever, here's how. So what we have over here is Codex plugged into our agent operating system, and then we can plug any free brain directly into it. So we can still use GPT 5.6 if we really want to, but for example, we could use a free API, like for example, OmniRoot inside chat-gpt-codex, and then that way we can get one of the best harnesses with a free API plugged into it. And I'll show you how that works in a second.

And then also the great thing about this is we have our workspace here, so anything that we create, we can come back to directly, and then all the powers, all the magic of Codex is directly inside this system. The other thing that I like about this is it's fully customizable, so for example, if I go into the normal Codex app, it's kind of messy, it's difficult to see things, it's difficult to organize, whereas with this system, it's all clean. We've got our chat here, we've got our goal mode over here, we can see our history, we can see our previous sessions, we can see our workspace, and it's just much easier to come back and keep everything organized. And also it works alongside, for example, our memory systems or Cloud Code or anything else we want to use.

Let me show you a side-by-side comparison over here. So if we go into chat-gpt and the normal sort of Codex app, this is what it normally looks like, right? And the problem with this is like, where's all your creations? Where's your workspace?

Where's everything you built? You can't find it. And then also, okay, but what happens if you run out of tokens? Well, you can't plug in the custom model into this normal app, right?

It's pretty difficult. And then also, you know, like there's different chats and there's different history of conversations that will be difficult to find over here. However, if we have a system like this, well, we can easily switch the brain like so. We can easily see everything that we've created over here.

We have all of our sessions, we have the goal mode and the chat. So now you're probably wondering, okay, where do you get OmniRoot? How do you set this up? So you can see OmniRoot over here on GitHub, and this basically gives you like 93 APIs, 93 models that you can plug into this system.

It also works not just with Codex, but also Cloud Chat GPT, OpenAI, whatever you want, right? All sorts of different harnesses here. The other thing that has is RTK and Caveman, which are two different token minimization systems, which means that you can basically get more tokens out of the free models as well, so that you don't get rate limited and you never stop coding, which is great because then you can code on free models without having to worry about getting rate limited or having to stop or switch models in between. The other great thing about this as well is like it automatically switches to a different model.

So if one of those free models fails, no problem, you can switch to another one instead. So let me show you an example of this. Let's say, for example, we like RTK. Build out a beautiful SEO website, and then you can see here that Codex is gonna start working its magic, and that's running in the background.

The other great thing about this was we can go off and we can use, for example, like Hermes Agent, which is one click away inside our system here, or we could use Claude, or we could use all of them together, and it doesn't disrupt what we're currently doing inside Codex. Plus, with OmniRoot, for example, you could plug this as a free brain into any other harness or agent. So let's say, for example, you really like Hermes. Well, you could get a free brain like OmniRoot and start using Hermes as a separate profile with OmniRoot directly there as well.

So it's a great system, and then additionally, this also plugs into your memory. So one of the biggest issues that you're gonna find if you're using, for example, ChatGPT and the app over here is that it doesn't sync, for example, with Claude Code. Everything that you do with Claude Code isn't synced up to ChatGPT. Why?

Because they don't have the shared memory between them. However, if you have a system that plugs a memory system, a shared memory system, into all of your AI agents and harnesses, like you can see right here, we're actually using Obsidian. And also, it looks super nice as well, so we can visualize it really easily. Then that will plug into Codex, into Hermes, into any other agent that we use, and it's automatically updated.

So we can have a look inside our memory system here, and it's like, okay, 42 minutes ago, we did this. 54 minutes ago, we did this. Three hours ago, we did this, right? And so our memories are being automatically updated by our AI agents.

I don't have to maintain it. I don't have to sync it. It is fully automated in the background. And so this is a powerful thing about using all this.

Now, we can also see the website that we've just created over here. So we can actually preview that, which is fantastic. We can open that up as well. So this was fully created with OmniRoot.

And here's the other thing. You might say, ah, you know, three models, not that good. But actually, if you look at this, like the website looks nice, it looks clean, it's pretty easy to use, and it works super fast. Like that was done in the background whilst I was talking to you.

The other thing that you might say is, AI models that are free, they often get rate limited. You can't get much out of them. But actually, this uses like 90 different models. So even if one gets rate limited, you can switch to another one and you don't even notice because it's automatically got auto fallback on them as well.

And then also with RTK and Caveman built in, you save about 15 to 95% of your tokens, which means that you don't hit the limits, which means that you can code for longer without being interrupted on free models as well. And you might also say, well, I don't want to use Codex. I want to use Claude. No problem, you can plug it into Claude code as well.

So for example, over here, we have free Claude code, and then we can actually switch in the dropdown between OmniRoot and NineRooter. So whatever we prefer to use, we can use over there as well. And so you're getting the best harness, but you're just changing the brain. You still got the same hands, which is really, really useful.

The other thing that we can do here as well is we can get the code, we can save it for later, we can add it to our workspace, and it's all automatically added over here, which is super useful and easy to use as well, which is great. Now, the final thing that I would say here is that when you've got a system like this, you can orchestrate your agents pretty cleanly and nicely. So for example, we have Paperclip over here, and you could have OmniRoot with Codex, you could have OmniRoot free Claude code, and you can have these as different agents being coordinated inside Paperclip over there as well. And then if you're like, oh, I don't want to use Codex, I just want to use the API directly, we actually have the free AI coder over here.

And what this allows you to do is you can prompt in the left-hand side, you can see your preview on the right-hand side, and then you can see everything that you've created over here. So the way that you can set this up, I mean, I'm non-technical, I just set up pretty quickly. What you can do is you can just grab OmniRoot and make sure that you've got ChatGBT already installed as the app, and you just go over to like Claude code or Codex, and you can say, listen, plug in Codex and start using that as a brain. And you don't need to be technical to set up that way, you don't need to follow any terminal commands that way as well, and it's super simple.

Now, what we've actually got over here is our agentic operating system. If you want to get this full system with all of the setups ready to go, so for example, OmniRoot and NineRoot are both free models, so you can plug into the free AI coder, you can use them with Codex, as I showed you a second ago, you could use them with, for example, free Claude code, whatever you want. You can get that inside the AI Profit Boardroom, link in the comments description or go to the AIProfitBoardroom.com. Inside this community, you can ask questions, get help and support in real time.

You can meet other members using stuff like this. And I personally answer your questions every single day with a video tutorial inside the community. Inside the classroom, you get access to all of my best trainings and this sort of stuff. So if you're a complete beginner, you can start with the Beginner to Expert Masterclass over here.

If you want the new stuff, you can go to the New Daily Update section and the Advanced Tutorial section, right? So however you want to learn, you've got everything. And also, if you want to get our full agentic operating system with a video tutorial, you can go to the AI Profit Boardroom.com. Thanks for watching.