Steve from Temporal here. Temporal is an MIT open source project for reliable execution at scale. I adapted+extended some of OpenAI's Agents SDK samples to integrate with Temporal.

These demo agents can survive process crashes, scale to millions of executions in parallel and have easy-to-implement human interactivity. Just add a couple of Python decorators to your OpenAI agent code, run Temporal workers and you're ready to go.

Check the video I did with OpenAI showing this in action (it's linked in the repo).

OpenAI actually use us for ChatGPT Images and also their Codex code writing agent so I figure this may be a viable path for others to code something easy that's also reliable at scale.

Happy to answer questions.

A thing that was interesting in reading through your code and comparing to the original repo's examples (https://github.com/openai/openai-agents-python/tree/main/exa...) is it's really not all that different. Some metadata to denote things as a workflow or activity and some different function calls but otherwise they seem quite similar.