OpenAI Agents is OpenAI’s Python framework for building agents — instructions, tools, handoffs, and theDocumentation 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.
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 package.
OpenAI Agents Tracing Tutorial (Google Colab)
OpenAI Agents Cookbook (Google Colab)
Prerequisites
- Python 3.10+
- An Arize AX account (sign up)
- An
OPENAI_API_KEYfrom the OpenAI Platform
Launch Arize AX
- Sign in to your Arize AX account.
- From Space Settings, copy your Space ID and API Key. You will set them as
ARIZE_SPACE_IDandARIZE_API_KEYbelow.
Install
Configure credentials
Setup tracing
Run OpenAI Agents
Expected output
Verify in Arize AX
- Open your Arize AX space and select project
openai-agents-tracing-example. - You should see a new trace within ~30 seconds containing an
responseparent span wrapping anAssistantagent span and an OpenAIChatCompletionLLM child span with the prompt, response, and token usage attached. - If no traces appear, see Troubleshooting.
Troubleshooting
- No traces in Arize AX. Confirm
ARIZE_SPACE_IDandARIZE_API_KEYare set in the same shell that runsexample.py. Enable OpenTelemetry debug logs withexport OTEL_LOG_LEVEL=debugand re-run. - Agents spans missing but other spans present.
OpenAIAgentsInstrumentor().instrument(...)must run before anyfrom agents import .... Make sureinstrumentation.pyis the first import in your entry point. 401from OpenAI. VerifyOPENAI_API_KEYis set and has access to the default model. Override withAgent(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 for examples that exercise both.