← back
OpenAI + @Temporalio : Building Durable, Production Ready Agents - Cornelia Davis, Temporal
Takeaway
Combining OpenAI's Agents SDK with Temporal turns agentic loops into durable, crash-tolerant workflows without the developer hand-coding retry, timeout and resume logic.
Summary
- Cornelia Davis (Temporal devrel) walks through pairing the OpenAI Agents SDK (Python/TS, launched ~May 2025) with Temporal — an integration the two companies built together for durable agentic workflows.
- Frames Temporal as 'distributed systems as a backing service' that gives durability — developers code the happy path while Temporal handles retries, crash recovery and resumable state; cites OpenAI Codex, OpenAI image gen, Snapchat, Airbnb, Pizza Hut and Lovable as Temporal users.
- Each runner.run in the Agents SDK is an agentic loop that calls the LLM, executes tools the LLM picks, feeds results back, and continues until the LLM signals done.
- Wrapping these loops in Temporal workflows means an agent that crashes mid-1,350-second turn can resume exactly where it left off, with rate limits and downstream API outages auto-retried by the SDK.
- Demos progress from a basic Agents SDK example to one orchestrated by Temporal showing handoffs, tool use and guardrails surviving failure injection.
agentsdurabilitytemporal
Original description
Everyone is building AI Agents, and everyone is looking for ways to build them more easily. Earlier this year, OpenAI released the OpenAI Agents SDK to bring the patterns they have found to work for building agents to the developer community. With the SDK you can define AI agents by supplying them instructions (prompts), specifying which model to use (OpenAI or not), listing tools it uses (including MCP), and much more. The OpenAI Agents SDK encourages a paradigm of orchestrated micro-agents, which themselves may have micro-orchestrations within them with the use of handoffs. It’s an elegant and powerful model. But a good AI Agents programming model is not enough. These agents are ultimately wildly distributed systems and are plagued with all of the problems such systems bring. - How can they persevere through flakey networks? - How can they function when LLMs are rate limited? - How can they run for long periods of time (hours, days, weeks, months) when infrastructure is rarely stable that long? In this workshop, we’ll show you how. Temporal is an open source (MIT license) durable execution framework that brings resilience to AI agents, and in this workshop we’ll show you how it’s done with the OpenAI Agents SDK. Spoiler: OpenAI and Temporal have done all of the heaving lifting for you with an integration announced earlier this year. Oh, and OpenAI themselves use Temporal to help make several of their products production ready (image gen and Codex, for example). Not using the OpenAI Agents SDK? Do come anyway; the foundational concepts carry over to different agent frameworks (and more integrations are coming all the time). https://twitter.com/cdavisafc https://www.linkedin.com/in/corneliadavis