Switchyard
Switchyard lets LLM applications route traffic across models
...It translates among OpenAI Chat, OpenAI Responses, and Anthropic Messages formats so agents can keep using their native APIs. Requests can be distributed across vLLM, NVIDIA NIM, Ollama, OpenRouter, and other compatible endpoints. Routing strategies include random splits, LLM classification, signal-driven stage routing, escalation, and custom algorithms. Prometheus metrics track requests, errors, latency, tokens, and routing overhead. Developers can run it as a standalone server, launch coding agents through it, or embed its routing logic in Rust applications. ...