Find guides, configuration references, deployment notes, and architecture documentation for AI Cost Firewall, vcal-core, and VCAL Server.
Documentation for the OpenAI-compatible gateway that reduces wasted LLM spend with exact and semantic caching.
Documentation for the core VCAL library and semantic matching foundation used across the VCAL ecosystem.
Documentation for the production semantic cache server designed for private AI infrastructure and enterprise deployment.
VCAL documentation is separated by product so each component can evolve independently, while this page stays as the stable entry point for the entire documentation ecosystem.
Use the gateway docs first if your goal is to reduce LLM cost, add request visibility, or run a quick local demo.
Use the core docs when you need lower-level concepts, developer integration guidance, or semantic cache internals.
Use the server docs when semantic caching becomes part of your production AI infrastructure.
