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 covers configuring the OpenClaw plugin, mapping OpenClaw hooks to NeMo Relay telemetry, and understanding current LLM replay fidelity boundaries.
LangChain Integration Guide covers installing the LangChain extra and adding NeMo Relay middleware and callbacks to LangChain agents.
LangGraph Integration Guide covers installing the LangGraph extra and adding NeMo Relay callbacks to LangGraph workflows.
Deep Agents Integration Guide 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 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 instead.