Find deployment guides, configuration references, architecture documentation, integration guidance, and operational notes for AI Cost Firewall and the broader VCAL infrastructure stack.
Documentation for the OpenAI-compatible gateway and orchestration layer for LLM traffic, caching, observability, production safeguards, and VCAL enterprise integrations.
Documentation for the production semantic cache server designed for private, shared, and high-volume AI infrastructure.
Commercial VCAL modules extend AI Cost Firewall with runtime protection, durable evidence, and compliance-oriented evaluation. Public integration guidance is available through AI Cost Firewall documentation today; dedicated module documentation sites will be added as each documentation source is separated.
VCAL documentation is separated by product responsibility so each component can evolve independently, while this portal remains the stable entry point for the overall documentation ecosystem.
Start here for LLM traffic control, caching, provider integration, observability, safeguards, and enterprise-module integration.
Use current AI Cost Firewall integration documentation for how Privacy Guard and Security Guard participate in request and response processing.
Start with AI Cost Firewall evidence-delivery documentation and product pages for Audit traceability and Compliance evaluation concepts.
Use the server docs when semantic caching becomes dedicated shared infrastructure for production AI workloads.
Open-source semantic matching library and foundation for developers who need lower-level concepts, reusable building blocks, or direct integration guidance.
Dedicated documentation sites for Privacy Guard, Security Guard, Audit, and Compliance will be added as those documentation sources are separated. Until then, this portal and AI Cost Firewall documentation provide the public integration entry points.
