engineering / agent

NVIDIA-NeMo/Switchyard

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.

Skills Outpost does not state this repository's requirements, supported systems or data practices. The repository on GitHub may describe them.

Code on GitHub

NVIDIA-NeMo/Switchyard

Apache-2.0

Rust3,445 GitHub stars343 GitHub forksLast pushed 26 Oct 2026 UTC

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.

Public GitHub data fetched · 0 days old

View on GitHub ↗
Report a listing concern

What did you see, and where? Please don't include passwords or keys.

We'll only use it to ask you about this report.