feat(relay): add Switchyard-owned HTTP dynamic plugin

CHANGELOG.md

@@ -6,6 +6,14 @@ adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
 
+### Added
+
+- **NeMo Relay native plugin** — a dynamically loaded integration that runs
+  libsy's weighted-random and LLM-classifier algorithms in process while
+  Switchyard owns provider HTTP dispatch, credentials, translation, retries,
+  and fallback. Managed calls require NeMo Relay 0.7 or newer and do not depend
+  on `switchyard-server`.
+
 ### Removed
 
 - **Latency-aware router** — the `latency_service` route type and its

Cargo.toml

@@ -12,6 +12,7 @@ members = [
     "crates/switchyard-server",
     "crates/switchyard-skill-distillation",
     "crates/switchyard-translation",
+    "crates/switchyard-nemo-relay-plugin",
 ]
 
 [workspace.package]
@@ -23,6 +24,7 @@ repository = "https://github.com/NVIDIA-NeMo/Switchyard"
 rust-version = "1.96.1"
 
 [workspace.dependencies]
+async-channel = "2"
 async-stream = "0.3"
 async-trait = "0.1"
 futures = "0.3"

README.md

@@ -21,6 +21,7 @@ algorithm you write yourself.
 - **Protocol Translation**: convert between OpenAI Chat, Anthropic Messages, and OpenAI Responses formats
 - **Multi-Backend Routing**: random routing, LLM-as-classifier routing, signal-driven stage-router, or your own algorithm
 - **Operational Metrics**: Prometheus metrics cover requests, errors, latency, tokens, and routing overhead
+- **NeMo Relay Plugin**: run random or LLM-classifier routing in Relay while Switchyard owns provider HTTP dispatch
 
 ## Quick Start
 
@@ -119,6 +120,7 @@ configured LLM client selects one upstream format.
 - **[`switchyard-libsy`](crates/libsy/README.md)**: embed routing algorithms in a Rust application
 - **[`switchyard-protocol`](crates/protocol/README.md)**: provider-neutral request, response, and streaming types
 - **[`switchyard-translation`](crates/switchyard-translation/README.md)**: request, response, and stream translation
+- **[`switchyard-nemo-relay-plugin`](crates/switchyard-nemo-relay-plugin/README.md)**: install Switchyard as a native NeMo Relay plugin
 
 ## Community
 

crates/switchyard-nemo-relay-plugin/Cargo.toml

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+[package]
+name = "switchyard-nemo-relay-plugin"
+version = "0.1.0"
+description = "Switchyard-owned HTTP routing plugin for NeMo Relay"
+authors.workspace = true
+edition.workspace = true
+license.workspace = true
+repository.workspace = true
+rust-version.workspace = true
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+async-channel.workspace = true
+async-trait.workspace = true
+futures-util.workspace = true
+http = "1"
+# Use the published release candidate during development. This becomes `0.7.0`
+# before the integration lands, after the stable crate is published.
+nemo-relay-plugin = "=0.7.0-rc.5"
+serde.workspace = true
+serde_json.workspace = true
+switchyard-libsy.workspace = true
+switchyard-llm-client.workspace = true
+switchyard-protocol.workspace = true
+switchyard-translation.workspace = true
+tokio.workspace = true