It's insane this update.

I hope they increase the quota and this is just a capacity issue.

But they basically killed it on the pro plan. Very disappointed and upset today, I've burnt through my weekly allowance on a handful of prompts trying to fix a bug that it's made worse. Now I can't use it for 6 days.

Cursor I guess, not the best one out there but if your coming from antigravity it’s not that much of a difference.

Or if your really tight in budget you could try Windsurfs „SWE-1.6“ model, currently free for pro users.

I use opencode with local Qwen 3.6 or GLM 4.7 models, running in llama.cpp, and am very happy with it for a lot of coding and code analysis work. Infinite tokens!

I have a Macbook Pro with M1 Max processor. I build llama.cpp from main every week or so, which I'm pretty sure includes Apple's 'metal' acceleration. That's it tho.

Yeah, and as much as people complain about Claude restrictions, it's a lot more generous than Antigravity and more transparent.