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.
Instructions file CodexOpenCode
Instructions for NVIDIA-NeMo/Switchyard, covering agents.md — switchyard, engineering guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.
Instructions file
Instructions for NVIDIA-NeMo/Switchyard, a project described as: 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.