Got rate limited mid-task yesterday and had to switch from Fable to GPT-5.6 Terra. 6 hours of back-and-forth context entirely gone.Lost 90 minutes just getting a different model up to speed on the project goals. Hitting a usage cap at the worst possible moment sucks. We desperately need a universal way to share context across different models.

@trikcode KruxOS / KruxCode has this - just switch model mid-conversation for full context, same memories, skills etc. switching mid conversation is obviously a brand new cache write so it's not recommended to do it every turn. but for cases like this it's perfect i need testers 🫡

@samelldev @trikcode Tell me more.

@cyburke @trikcode shoot me a DM, happy to answer anything!