nwhitehouse locks the fork to a single AI engine
The fork formerly known as Finch is now Olava - and it only talks to one model.
nwhitehouse has stripped every other AI provider out of this fork. The model picker, which used to let users choose between Anthropic's Claude and Google's Gemini, now offers exactly one option: Olava-001. Even if a returning user has an older model saved in their browser, the server quietly rewrites the request to use Olava anyway.
The "bring your own API key" screen is gone too. Users don't supply credentials anymore - the Olava endpoint is wired in at the infrastructure level, and that's the only path in. Alongside the lockdown, the team finished a full rename from Finch to Olava across the interface, sidebar, logo, exported documents, and the legal links in signup. It reads less like a fork experimenting with AI and more like a product getting ready to ship.
Spotted something wrong? Or know the PR text has fresher detail than the writeup above?