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

# Quick Starts

> Choose the shortest NeMo Relay path for your agent, framework, or application.

Choose the runtime or language you already use. Relay attaches where your
agent, framework, or application owns model requests and tool execution.

> **Note**
>
> Relay has no required or default model. Each guide that makes live
> inference requests identifies the credentials and model access it needs.
> The application API examples below use local callbacks.

## Agent Harnesses

When a coding-agent runtime owns invocation, start with
[CLI Basic Usage](/nemo-relay-cli/basic-usage). For persistent Claude Code or
Codex installation, use [Coding Agent Installation](/nemo-relay-cli/plugin-installation).
For agent-owned integrations, refer to
[Supported Integrations](/supported-integrations/about).

#### [Codex](/getting-started/quick-start/codex)

Run one Codex CLI task with Relay model and tool observability.

#### [Claude Code](/getting-started/quick-start/claude-code)

Run one Claude Code session with Relay model and tool observability.

#### [Hermes Agent](/getting-started/quick-start/hermes)

Configure Hermes Agent's native Relay observability and run one agent turn.

#### [pi](/getting-started/quick-start/pi)

Install the proof-of-concept extension and observe one pi task.

## Featured Plugins

For reusable runtime behavior, start with
[Plugin Configuration Files](/configure-plugins/plugin-configuration-files).

## Agent Frameworks

If a framework owns callbacks or tool execution, choose its path in
[Supported Integrations](/supported-integrations/about).

#### [Deep Agents](/getting-started/quick-start/deep-agents)

Run one Deep Agents workflow with Relay's maintained integration.

#### [LangChain](/getting-started/quick-start/langchain)

Run one tool-using agent with Relay middleware and callbacks.

#### [LangGraph](/getting-started/quick-start/langgraph)

Run one credential-free graph with Relay callbacks.

## Application APIs

Use these paths when your application directly owns the tool or model call.

#### [Python](/getting-started/quick-start/python)

Instrument application-owned Python calls.

#### [Node.js](/getting-started/quick-start/nodejs)

Instrument application-owned Node.js calls.

#### [Rust](/getting-started/quick-start/rust)

Instrument application-owned Rust calls.

## For More Details

For installation and exporter options, refer to:

* [Installation Overview](/getting-started/installation)
* [Observability](/configure-plugins/observability/about)

> Choose the shortest NeMo Relay path for your agent, framework, or application.

## Docs

- [Deep Agents Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/deep-agents.md): Run one Deep Agents workflow with NeMo Relay observability.
- [LangChain Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/langchain.md): Run one LangChain agent with NeMo Relay observability.
- [LangGraph Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/langgraph.md): Run one LangGraph workflow with NeMo Relay observability.
- [Codex Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/codex.md): Run one local Codex CLI task through NeMo Relay and write ATOF events.
- [Claude Code Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/claude-code.md): Run one local Claude Code session through NeMo Relay and write ATOF events.
- [Hermes Agent Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/hermes.md): Run one Hermes Agent turn with native NeMo Relay observability.
- [pi Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/pi.md): Run one local pi task through NeMo Relay and write ATOF events.
- [Python Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/python.md): Instrument one Python workflow and write its Relay events to a local ATOF file.
- [Node.js Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/nodejs.md): Instrument one Node.js workflow and write its Relay events to a local ATOF file.
- [Rust Quick Start](https://docs.nvidia.com/nemo/relay/dev/getting-started/quick-start/rust.md): Instrument one Rust workflow and write its Relay events to a local ATOF file.