> 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

Use this section when your application already uses a supported framework or
agent harness and you want the maintained NeMo Relay integration path for that
surface.

Supported integrations are end-user entry points. They use public framework or
plugin APIs where available and document the support level for observability,
security middleware, and optimization features.

## Support Matrix

| Agent / Library | Observability | Security | Optimization | Notes                                                                                                  |
| :-------------- | :-----------: | :------: | :----------: | :----------------------------------------------------------------------------------------------------- |
| LangChain       |      Yes      |    Yes   |      Yes     | Wrapped tool and LLM calling.                                                                          |
| LangGraph       |      Yes      |    Yes   |      Yes     | Wrapped tool and LLM calling.                                                                          |
| Deep Agents     |      Yes      |    Yes   |      Yes     | Wrapped tool and LLM calling.                                                                          |
| Google ADK      |      Yes      |    Yes   |      Yes     | Record model and tool calls and apply guardrails with the ADK plugin.                                  |
| OpenClaw        |      Yes      |  Partial |      No      | Hook-backed telemetry with pre-tool guardrails. Public hooks do not expose managed execution rewrites. |

## Guides

Use these guide links to move from the support matrix into setup and usage
instructions.

* [OpenClaw Plugin Guide](/nemo/relay/v0.11.0/supported-integrations/openclaw-plugin) covers configuring the OpenClaw
  plugin, mapping OpenClaw hooks to NeMo Relay telemetry, and understanding
  current LLM replay fidelity boundaries.
* [LangChain Integration Guide](/nemo/relay/v0.11.0/supported-integrations/langchain) covers installing the LangChain
  extra and adding NeMo Relay middleware and callbacks to LangChain agents.
* [LangGraph Integration Guide](/nemo/relay/v0.11.0/supported-integrations/langgraph) covers installing the LangGraph
  extra and adding NeMo Relay callbacks to LangGraph workflows.
* [Deep Agents Integration Guide](/nemo/relay/v0.11.0/supported-integrations/deepagents) covers installing the Deep
  Agents extra and capturing Deep Agents-specific marks, skills, subagents, and
  human-in-the-loop lifecycle events.
* [Google ADK Integration Guide](/nemo/relay/v0.11.0/supported-integrations/google-adk) covers installing the Google
  ADK extra, adding the plugin to your app, and recording workflows. It also
  explains which tools Relay can protect.

Across LangChain, LangGraph, Deep Agents, and Google ADK, instrumented tool lifecycles also
inherit Relay's automatic `skill.load` detection when a tool requests a
complete `SKILL.md` read.

If you are building a new public-API framework integration,
use [Integrate into Frameworks](/nemo/relay/v0.11.0/integrate-into-frameworks/about) instead.