> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# OpenAI Agents SDK
> Trace OpenAI Agents SDK runs with OpenInference and send spans to Arize AX for LLM observability.
[OpenAI Agents](https://github.com/openai/openai-agents-python) is OpenAI's Python framework for building agents — instructions, tools, handoffs, and the `Runner` that drives them. Arize AX captures every Agents SDK run — agent invocations, tool calls, handoffs, and the underlying LLM calls — via the [`openinference-instrumentation-openai-agents`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-openai-agents) package.
## Prerequisites
* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* An `OPENAI_API_KEY` from the [OpenAI Platform](https://platform.openai.com/api-keys)
## Launch Arize AX
1. Sign in to your [Arize AX account](https://app.arize.com/).
2. From **Space Settings**, copy your **Space ID** and **API Key**. You will set them as `ARIZE_SPACE_ID` and `ARIZE_API_KEY` below.
## Install
```bash theme={null}
pip install arize-otel \
openinference-instrumentation-openai-agents \
openai-agents openai
```
## Configure credentials
```bash theme={null}
export ARIZE_SPACE_ID=""
export ARIZE_API_KEY=""
export ARIZE_PROJECT_NAME="openai-agents-tracing-example"
export OPENAI_API_KEY=""
```
## Setup tracing
```python theme={null}
# instrumentation.py
import os
from arize.otel import register
from openinference.instrumentation.openai_agents import (
OpenAIAgentsInstrumentor,
)
tracer_provider = register(
space_id=os.environ["ARIZE_SPACE_ID"],
api_key=os.environ["ARIZE_API_KEY"],
project_name=os.environ["ARIZE_PROJECT_NAME"],
)
OpenAIAgentsInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for OpenAI Agents.")
```
## Run OpenAI Agents
```python theme={null}
# example.py
# Importing instrumentation first ensures tracing is set up
# before `agents` is imported.
from instrumentation import tracer_provider
from agents import Agent, Runner
# The agent reads OPENAI_API_KEY from the environment.
agent = Agent(
name="Assistant",
instructions="You are a concise factual assistant.",
)
result = Runner.run_sync(
agent,
"Why is the ocean salty? Answer in two sentences.",
)
print(result.final_output)
```
### Expected output
```text wrap theme={null}
Arize AX tracing initialized for OpenAI Agents.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.
```
## Verify in Arize AX
1. Open your Arize AX space and select project **`openai-agents-tracing-example`**.
2. You should see a new trace within \~30 seconds containing an `response` parent span wrapping an `Assistant` agent span and an OpenAI `ChatCompletion` LLM child span with the prompt, response, and token usage attached.
3. If no traces appear, see [Troubleshooting](#troubleshooting).
## Troubleshooting
* **No traces in Arize AX.** Confirm `ARIZE_SPACE_ID` and `ARIZE_API_KEY` are set in the same shell that runs `example.py`. Enable OpenTelemetry debug logs with `export OTEL_LOG_LEVEL=debug` and re-run.
* **Agents spans missing but other spans present.** `OpenAIAgentsInstrumentor().instrument(...)` must run before any `from agents import ...`. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from OpenAI.** Verify `OPENAI_API_KEY` is set and has access to the default model. Override with `Agent(model="gpt-5", ...)` for a model your key can call.
* **Tool / handoff spans expected but not present.** Tool-calling and handoffs only emit spans when the agent actually invokes them. The minimal example above has neither — see the [OpenAI Agents Cookbook](https://colab.research.google.com/github/Arize-ai/tutorials/blob/main/python/llm/agents/openai-agents-cookbook.ipynb) for examples that exercise both.
## Resources