NeMo Relay Deep Agents Integration

Use the nemo_relay.integrations.deepagents package to add NeMo Relay observability to Deep Agents applications through the LangChain and LangGraph integration surfaces that Deep Agents builds on.

Setup

Install the Deep Agents integration extra in your application environment.

$
uv add "nemo-relay[deepagents]"

The example below uses the NVIDIA LangChain provider. Install that provider extra too if you want to run the example as written:

$
uv add "nemo-relay[deepagents,langchain-nvidia]"

Usage Example

1
import nemo_relay
2
from deepagents import create_deep_agent
3
from nemo_relay.integrations.deepagents import (
4
    NemoRelayDeepAgentsCallbackHandler,
5
    add_nemo_relay_integration,
6
)
7
8
agent = create_deep_agent(
9
    **add_nemo_relay_integration(
10
        model="nvidia:nvidia/nemotron-3-nano-30b-a3b",
11
        tools=[],
12
        name="main-agent",
13
    )
14
)
15
16
input_payload = {
17
    "messages": [
18
        {
19
            "role": "user",
20
            "content": "Research recent GPU news",
21
        }
22
    ]
23
}
24
25
with nemo_relay.scope.scope("deepagents-request", nemo_relay.ScopeType.Agent):
26
    result = agent.invoke(
27
        input_payload,
28
        config={"callbacks": [NemoRelayDeepAgentsCallbackHandler()]},
29
    )
30
31
final_message = result["messages"][-1]
32
print(f"Final response: {final_message.content}")

Add skills=[...] or subagent configuration after this minimal path is working when you need to capture Deep Agents skill or subagent marks.

Verify the Integration

The integration works correctly when:

• The Deep Agents run completes and prints a final response.
• The deepagents-request scope contains the top-level agent execution.
• Skill, subagent, and human-in-the-loop marks appear when those features are exercised.

Observability

The integration composes the existing NeMo Relay LangChain and LangGraph hooks, then emits Deep Agents-specific marks for configured skills, subagents, and human-in-the-loop lifecycle events.

It captures:

• LangChain model and tool calls through NeMo Relay managed execution.
• LangGraph run scopes through callbacks.
• Human-in-the-loop interrupt and resume marks.
• Configured skills and subagent summaries at agent-run start.
• In-process dictionary-style subagents with the same NeMo Relay middleware, so their model and tool calls are captured when Deep Agents invokes them.

Remote graphs or processes still need NeMo Relay instrumentation in that graph or process to capture their internal model and tool calls.

Refer to Observability for details on exporting NeMo Relay observability data to third-party systems.