Hit your Cursor usage limit?

What you'll see

Cursor shows a notification in the editor and offers on-demand usage or a higher plan.

Keep working through the wall

Launch your agent through OpenLLM and give its model alias a fallback chain. When your Cursor Pro allowance is exhausted, that entry is cooled and the request continues on the next plan or API key you hold.

• ▸openllm claude
• ▸openllm codex
• ▸openllm opencode

Why not inside Cursor?

A fallback chain can't run inside the Cursor editor on your other subscriptions: Cursor sends custom-model requests from its own servers, which can't reach the daemon on your machine. What works is a terminal agent launched through OpenLLM on another plan you hold, with Cursor as one more entry in the chain.

Fallback chains when a model is rate-limited

Define an ordered chain per model alias. When a hop returns a rate limit, an overload or a provider error, the request moves to the next hop instead of failing your session.

• ▸Chains are configured once and shared by every client and device
• ▸Each hop resolves its own model settings, so a fallback never inherits the wrong parameters
• ▸Every hop that ran is visible in your request history