Have you ever wanted to use Cursor and not have your prompts run in Elon's data centers?
Now you can use co/core to run that same work on some random person's extra computer!
1. Create an api key in your user settings on console.cocore.dev => put in cursor model settings
2. Add cocore as your openai url => console.cocore.dev/v1
3. Choose a model from console.cocore.dev/models and add it to the models list
4. Switch your chats to use that model
It only took me... ~165k tokens. And I was only really calling co/core for testing! Mostly I used a local Qwen 3.6 35B and Deepseek v4 Pro.
I created a new Pi extension to use co/core for it's model backend: github.com/willnewby/pi..., so far it's working!
CC @cocore.dev
Saving my @cocore.dev tokens for a Papa John's pizza
