> ## Documentation Index
> Fetch the complete documentation index at: https://docs.negentro.tech/llms.txt
> Use this file to discover all available pages before exploring further.

# Redis Semantic Caching

> Ultra-low latency semantic caching layer and token budget acceleration.

Redis provides sub-millisecond query caches, distributed token rate limiters, and session mining buffers for live conversational handoffs.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.