> This page is for NeMo Relay, version v0.11.0.
> For other versions, use one of these documentation indexes:
> - Latest (v0.10.4) (default): https://docs.nvidia.com/nemo/relay/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/relay/dev/llms.txt
> - v0.11.0: https://docs.nvidia.com/nemo/relay/v0.11.0/llms.txt
> - v0.10.4: https://docs.nvidia.com/nemo/relay/v0.10.4/llms.txt
> - v0.9.4: https://docs.nvidia.com/nemo/relay/v0.9.4/llms.txt
> - v0.8.4: https://docs.nvidia.com/nemo/relay/v0.8.4/llms.txt
> - v0.7.3: https://docs.nvidia.com/nemo/relay/v0.7.3/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# About

> Choose where NeMo Relay attaches to your agent system.

NeMo Relay observes and controls agent work at the boundary where it runs.
Choose the path that matches the agent runtime, framework, or application you
already use.

## Choose Where Relay Attaches

Use the boundary that owns the model request or tool execution:

* **Agent runtime:** Observe a coding agent without changing application code.
* **Framework:** Use a maintained integration when the framework owns callbacks
  and tool execution.
* **Application:** Instrument Python, Node.js, or Rust code when your
  application owns the tool or model call.

You do not need a Rust compiler, a source checkout, or repository development
tools to install a published CLI binary.

## Try Relay Now

#### [Quick Starts](/nemo/relay/v0.11.0/getting-started/quick-start)

Choose the shortest path for your runtime or application, then verify its output.

## Using an AI Coding Assistant

#### Using an AI Coding Assistant?

Install [NVIDIA agent skills](https://docs.nvidia.com/skills) to give
compatible coding agents product-specific Relay workflows and references. After
the NeMo Relay skills are published in `nvidia/skills`, install the full Relay
skill set without cloning the catalog:

```bash
npx skills add nvidia/skills \
  --skill nemo-relay-install \
  --skill nemo-relay-get-started \
  --skill nemo-relay-instrument-calls \
  --skill nemo-relay-instrument-context-isolation \
  --skill nemo-relay-instrument-typed-wrappers \
  --skill nemo-relay-plugin-observability \
  --skill nemo-relay-plugin-adaptive-tuning \
  --skill nemo-relay-plugin-build \
  --skill nemo-relay-migrate-from-flow \
  --skill nemo-relay-debug-runtime-integration \
  --agent codex
```

Use `--agent claude-code`, `--agent cursor`, or another supported agent target
when that is where you want the skill installed. To inspect the current NVIDIA
skill catalog first, run:

```bash
npx skills add nvidia/skills --list
```

Agent skills help your coding assistant apply Relay documentation and workflows.
They do not replace installing NeMo Relay packages, configuring runtime
plugins, or validating emitted events.

## Go Beyond the First Run

After a working first run, choose an advanced path to build reusable behavior
or operate Relay as a long-running service:

#### [Build a Plugin](/nemo/relay/v0.11.0/build-plugins/about)

Create reusable behavior that observes or controls agent work.

#### [Deploy a Daemon](/nemo/relay/v0.11.0/daemon/about)

Run Relay as a managed service for local users or remote clients.

For deeper guidance, refer to:

* [Installation Overview](/nemo/relay/v0.11.0/getting-started/installation): Compare packages,
  supported platforms, and alternative installers.
* [Configuration / Setup Overview](/nemo/relay/v0.11.0/getting-started/configuration): Configure
  runtime behavior and plugins in more detail.
* [Development Setup](/nemo/relay/v0.11.0/contribute/development-setup): Build from source or
  contribute to the repository.
* [Agent Runtime Primer](/nemo/relay/v0.11.0/about-nemo-relay/agent-runtime-primer) and
  [Concepts](/nemo/relay/v0.11.0/about-nemo-relay/concepts): Understand the runtime model.
* [Integrate into Frameworks](/nemo/relay/v0.11.0/integrate-into-frameworks/about): Build custom
  framework integrations.