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.
Rust
docs(readme): update README to contain Agent Router (#1313)
Nick DiZazzo287365fbd9ab
diff --git a/README.md b/README.mdindex 170a9eb1e..ab0cb8225 100644--- a/README.md+++ b/README.md@@ -45,9 +45,10 @@ Evaluate the complete agent, model pool, and routing configuration against your| Gateway | Start here | Deployment and limits || --- | --- | --- |-| **OpenRouter** | [Use Switchyard through OpenRouter](https://openrouter.ai/docs/guides/routing/routers/switchyard-router) | Hosted by OpenRouter. Set `model` to `nvidia/switchyard` in API requests. |+| **Agent Router** | [Agent Router](https://github.com/tetratelabs/built-on-envoy/blob/main/extensions/switchyard/README.md) | Open-source and self-hosted. It provides an OpenAI-compatible API and runs on Envoy. || **LiteLLM** | [Run the Switchyard routing-plugin example](examples/litellm/README.md#quick-start-with-the-local-proxy) | Experimental and checkout-only. The example pins LiteLLM 1.102.0 and supports Stage routing based on request history, plus Random routing. It cannot service intermediate model calls required by classifier or escalation algorithms. || **NeMo Relay** | [Build and configure the native plugin](crates/switchyard-nemo-relay-plugin/README.md#build-from-source) | Requires Relay `>=0.10.0, <1.0.0`. The source-build path requires a Rust toolchain and Python 3. |+| **OpenRouter** | [Use Switchyard through OpenRouter](https://openrouter.ai/docs/guides/routing/routers/switchyard-router) | Hosted by OpenRouter. Set `model` to `nvidia/switchyard` in API requests. |Relay 0.8.x and 0.9.0 can lose upstream error status and details when the pluginis enabled, even for models outside its routes. Review the