Developer creates Cursor extension to prevent costly LLM cache expiration mistakes by tracking context window timers

Built by a developer at Ploid AI to address common cache-related errors that waste money and context

Tracks LLM cache TTL (time-to-live) timers so users can see when context cache is about to expire

Solves two primary issues: forgetting to continue the right chat and losing context/cost due to cache dropoff timing mistakes

Available on Open VSX marketplace with source code on GitHub for community feedback and contributions