Simple examples to get started with OpenAI Agents SDK integrated with Temporal workflows.

Adapted from OpenAI Agents SDK basic examples

Before running these examples, be sure to review the prerequisites and background on the integration.

First, start the worker (supports all basic examples):

uv run openai_agents/basic/run_worker.py

Then run individual examples in separate terminals:

Basic agent that only responds in haikus:

uv run openai_agents/basic/run_hello_world_workflow.py

Agent with access to external tools (simulated weather API):

uv run openai_agents/basic/run_tools_workflow.py

Demonstrates agent lifecycle events and handoffs between agents:

uv run openai_agents/basic/run_agent_lifecycle_workflow.py

Shows detailed usage tracking with RunHooks (requests, tokens, etc.):

uv run openai_agents/basic/run_lifecycle_workflow.py

Agent with dynamic instruction generation based on context (haiku/pirate/robot):

uv run openai_agents/basic/run_dynamic_system_prompt_workflow.py

Demonstrates different JSON schema validation approaches:

uv run openai_agents/basic/run_non_strict_output_workflow.py

Note: CustomOutputSchema is not supported by the Temporal OpenAI Agents SDK integration and is omitted in this example.

Process local image files with AI vision:

uv run openai_agents/basic/run_local_image_workflow.py

Process remote image URLs with AI vision:

uv run openai_agents/basic/run_remote_image_workflow.py

Demonstrates conversation continuity using response IDs:

uv run openai_agents/basic/run_previous_response_id_workflow.py

The following examples from the reference repository are not included in this Temporal adaptation:

• Session - Stores state in local SQLite database, not appropriate for distributed workflows
• Stream Items/Stream Text - Streaming is not supported in Temporal OpenAI Agents SDK integration