Here is the honest version: I was ready to cancel my Anthropic Claude subscription. Not "thinking about it" ready. Decided ready.
T3 Code is the single reason I stayed.
That is not a figure of speech. I had a company deal that let me get a ChatGPT Pro subscription, so the money argument was firmly on ChatGPT's side. I tried Codex properly. And I liked it. After a week or two with Codex and the newer GPT models, I had made up my mind that my personal subscription would move from Claude to ChatGPT.
Then I tried one tool, and the decision flipped. This post is why.
Very close. Close enough that I had told myself it was done.
The setup was almost perfect for ChatGPT. The subscription would have cost me effectively nothing through the company deal. And Codex was, honestly, amazing to use.
So this is not a case of me defending a tool I was already loyal to. I was walking out the door.
I went into agentic work biased against it. I am the person who needs the project cleaned up. I want the folder structure visible. I want to see what is happening, step by step, not trust a black box to poke around my files.
Agentic here just means the AI can act on its own across your project, running tasks and touching files instead of only answering in a chat box.
Codex got me past that bias, mostly through design. It felt calm and readable. And I genuinely loved the computer use and the agentic side of it. Unlike a chat sidebar stuck to one window, I could work across multiple projects at the same time. For a freelancer juggling a few clients at once, that is not a nice-to-have. That is the whole job.
Before all this, I ran Cursor, with Claude Code working inside Cursor.
It was not bad. But two things nagged at me.
I did not want to set up API keys by hand every time. And I wanted to run Claude Code across several projects at once, which was not really possible that way.
So the exact thing that pulled me toward Codex was a workflow gap, not brand love. Codex solved the multi-project problem. Claude, in the setup I had, did not.
Then I tried T3 Code.
I have written about T3 Chat before, so if you have read that you already know I am a fan of Theo's work. (If you missed it, that post is on the blog.)
T3 Code is what kept me on Anthropic. It is great to use, and the design is, if anything, even better than what pulled me toward Codex in the first place. It even has a thing called T3 Connect, which lets you manage your sessions remotely from your smartphone for example.
You can even connect your other subscriptions easily. Still, crazy to think that the best AI experience comes from an indie developer.
And here is the key part: it solves the multi-project problem. The exact gap that was pushing me to switch is the thing T3 Code fixed.
A few concrete reasons, not vibes:
It is only fair to name why the shine came off Codex, too.
After ChatGPT and Codex got merged, the input on Windows got weird. Sometimes it lags.
Small thing. But it is the thing you touch every single minute. Friction in the one spot you never stop using adds up fast.
I am not going to pretend it is perfect.
The one thing I still miss is computer use, the way ChatGPT does it. That real, hands-on-the-machine agentic control is not there in the same way yet.
I have heard it is in development. I hope so, because that is the last gap between "the tool I stayed for" and "the tool I would recommend to almost anyone."
If you are on Linux and you try T3 Code, do this.
This is my experience over a few weeks, not a benchmark. I did not run controlled tests. I ran my actual work.
I am one freelancer on Ubuntu with a specific multi-project workflow. Your bottleneck might be somewhere else entirely. If your pain point is computer use, Codex might still be your pick. If you live on Windows, weigh that input lag for yourself.
But if you are, like I was, one click away from cancelling Claude, do yourself a favour and try T3 Code first. It changed my answer.
Thanks for reading. If you want to compare notes on your own AI tooling setup, reach out, the links are in the footer.