OpenAI Agents SDK

Choose a setup method

Method	Use it when
Voxmith skill	You want your coding agent to inspect the app, make the change, and verify it.
Voxmith SDK	You want explicit control over the interaction boundaries and fields.
OpenTelemetry	The framework already emits useful spans or you operate an OTel pipeline.

Start with one method for a call path. Combining SDK tracking with framework OpenTelemetry on the same call can create duplicate interactions.

Recommended: Voxmith skill

Recommended. Choose this path when you want your coding agent to inspect the project, select a supported transport, make the smallest instrumentation change, send a test event, and verify that it reached Voxmith.

Install the skill once in your coding-agent environment:

npx skills add Voxmith/skills --skill voxmith

Run the framework-specific prompt below from the application root. Review the resulting diff before deploying it.

Use the voxmith skill to add Voxmith analytics to this OpenAI Agents application.
Org ID: your-org-id
Instrument the real Runner call and verify one fresh interaction.

Manual setup: Voxmith SDK

pip install voxmith

import voxmith
from agents import Runner

voxmith.init("your-org-id")
interaction = voxmith.begin(user_id="u-42", agent_name="openai-agent", input=prompt)
try:
    result = Runner.run_sync(agent, prompt)
    interaction.end(output=str(result.final_output))
except Exception as exc:
    interaction.end(output=str(exc), success=False)
    raise
finally:
    voxmith.shutdown()

Manual setup: OpenTelemetry

Install

pip install openai-agents openinference-instrumentation-openai-agents \
            opentelemetry-sdk opentelemetry-exporter-otlp-proto-http

Setup

import os
from agents import set_tracing_disabled
from openinference.instrumentation.openai_agents import OpenAIAgentsInstrumentor
from openinference.instrumentation import using_attributes
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://otel.voxmith.com"
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = "X-Voxmith-Org-ID=<your-org-id>"

set_tracing_disabled(True)  # turn off OpenAI's hosted trace backend

provider = TracerProvider()
provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
trace.set_tracer_provider(provider)
OpenAIAgentsInstrumentor().instrument(tracer_provider=provider)

with using_attributes(session_id="sess-123", user_id="u-42"):
    await Runner.run(agent, "Hello")

You get agent / handoff / guardrail spans plus the underlying LLM call spans with full message and tool data (llm.input_messages.*, llm.output_messages.*, tool.name, tool.parameters, llm.token_count.*).

Caveats

Without set_tracing_disabled(True), traces also flow to OpenAI's hosted dashboard.

Verify

Run one Runner.run call, then open Events in Voxmith. Confirm agent, handoff, guardrail, and LLM spans are present.

Troubleshooting

Call set_tracing_disabled(True) if you do not want dual-send to OpenAI's hosted trace backend.
Confirm OTEL_EXPORTER_OTLP_HEADERS contains X-Voxmith-Org-ID=<your-org-id>.
Confirm using_attributes wraps the call you want grouped.

References

Next steps

Conversations: review the complete agent run.
Events: inspect model calls, handoffs, guardrails, and tools.
Intents: organize production conversations by what users wanted.