> ## Documentation Index
> Fetch the complete documentation index at: https://puzzlet-9ba7bb98.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Agents SDK

> Trace OpenAI Agents SDK runs in AgentMark using the OpenInference instrumentor, in Python and JavaScript.

export const props_0 = undefined

export const subject_0 = "OpenAI Agents"

The OpenInference `OpenAI Agents` instrumentor instruments the [OpenAI Agents SDK](https://github.com/openai/openai-agents-python), bridging the SDK's native tracing into OTLP spans: agent runs, handoffs, tool calls, and model calls. Point the exporter at AgentMark and the traces arrive normalized.

## Setup

<Steps>
  <Step title="Install the instrumentor and the OTLP exporter">
    <CodeGroup>
      ```bash TypeScript theme={null}
      npm install @arizeai/openinference-instrumentation-openai-agents @openai/agents \
        @opentelemetry/sdk-trace-node @opentelemetry/sdk-trace-base \
        @opentelemetry/exporter-trace-otlp-http
      ```

      ```bash Python theme={null}
      pip install openinference-instrumentation-openai-agents \
        opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
      ```
    </CodeGroup>
  </Step>

  <Step title="Point the exporter at AgentMark and instrument the SDK">
    Use your AgentMark API key and app id from project settings.

    <CodeGroup>
      ```typescript TypeScript theme={null}
      // instrumentation.ts
      import { NodeTracerProvider } from "@opentelemetry/sdk-trace-node";
      import { BatchSpanProcessor } from "@opentelemetry/sdk-trace-base";
      import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http";
      import { OpenAIAgentsInstrumentation } from "@arizeai/openinference-instrumentation-openai-agents";
      import * as agents from "@openai/agents";

      const provider = new NodeTracerProvider({
        spanProcessors: [
          new BatchSpanProcessor(
            new OTLPTraceExporter({
              url: "https://api.agentmark.co/v1/traces",
              headers: {
                Authorization: process.env.AGENTMARK_API_KEY!, // raw key, no "Bearer" prefix
                "X-Agentmark-App-Id": process.env.AGENTMARK_APP_ID!,
              },
            })
          ),
        ],
      });
      provider.register();

      const instrumentation = new OpenAIAgentsInstrumentation({ tracerProvider: provider });
      instrumentation.manuallyInstrument(agents);
      ```

      ```python Python theme={null}
      from openinference.instrumentation.openai_agents import OpenAIAgentsInstrumentor
      from opentelemetry.sdk.trace import TracerProvider
      from opentelemetry.sdk.trace.export import BatchSpanProcessor
      from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

      provider = TracerProvider()
      provider.add_span_processor(
          BatchSpanProcessor(
              OTLPSpanExporter(
                  endpoint="https://api.agentmark.co/v1/traces",
                  headers={
                      "Authorization": "<YOUR_API_KEY>",  # raw key, no "Bearer" prefix
                      "X-Agentmark-App-Id": "<YOUR_APP_ID>",
                  },
              )
          )
      )

      OpenAIAgentsInstrumentor().instrument(tracer_provider=provider)
      ```
    </CodeGroup>

    <Note>
      In TypeScript, this setup must run **before** the agents SDK runs, so the instrumentor can register its trace processor. Put it in its own module and load it first, for example `node -r ./instrumentation.js app.js`.
    </Note>
  </Step>

  <Step title="Run your agent">
    Run your agent as usual. Each agent run, handoff, tool call, and model call arrives in AgentMark as a span, grouped into a trace. See [Traces and logs](/observe/traces-and-logs).
  </Step>
</Steps>

## What AgentMark captures

{props_0.subject_0} spans use the OpenInference attribute conventions: model, token usage, input and output messages, tool calls, settings, and span kind are all mapped onto AgentMark's normalized trace fields, and token counts feed [cost tracking](/observe/cost-and-token-tracking). See [OpenInference](/integrations/tracing/openinference#what-agentmark-captures) for the full attribute mapping.

## Next steps

<CardGroup cols={2}>
  <Card title="OpenInference" icon="diagram-project" href="/integrations/tracing/openinference">
    How AgentMark reads OpenInference attributes
  </Card>

  <Card title="Traces and logs" icon="list-tree" href="/observe/traces-and-logs">
    Explore traces once they arrive
  </Card>
</CardGroup>

<div className="mt-8 rounded-lg bg-blue-50 p-6 dark:bg-blue-900/30">
  <h3 className="font-semibold mb-3">Have questions?</h3>
  <p className="mb-4">Reach out any time:</p>

  <ul>
    <li>
      Email the team at <a href="mailto:hello@agentmark.co" className="text-blue-600 hover:text-blue-800 dark:text-blue-400 dark:hover:text-blue-200">[hello@agentmark.co](mailto:hello@agentmark.co)</a> for support
    </li>

    <li>
      Schedule an <a href="https://cal.com/ryan-randall/enterprise" className="text-blue-600 hover:text-blue-800 dark:text-blue-400 dark:hover:text-blue-200">Enterprise Demo</a> to learn about AgentMark's business solutions
    </li>
  </ul>
</div>