Lars-confi/RealityRouter

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No database required, built-in cost tracking, budget enforcement and multi-tenant isolation.

A self-hostable LLM router / gateway: OpenAI- and Anthropic-compatible, explicit-first routing with fallbacks, spend limits, and metadata-only cost tracking. No markup, no third-party proxy — your keys, your box.

The minimal interpretable model router that learns & adapts to your agent workflows

Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.

Route every prompt to the best LLM — for you specifically.

An open, programmable decision layer for models and compute.