You can now build and deploy long-running, tool-using agents with the OpenAI Agents API on Vercel. OpenAI manages the agent loop and session state, while Vercel hosts the application and connects each session to Vercel Sandbox for code execution and file access.
With this integration, you get:
An OpenAI-managed agent loop and session state
Reliable Sandbox creation and reconnection through signed OpenAI webhooks and Vercel Queues
An isolated execution environment for every agent session
A persistent workspace that retains files across follow-up instructions
A scale-to-zero architecture without an always-on worker Follow the step-by-step guide to build and deploy an agent, or explore the sample application.
source & further reading
vercel.com — original article
How Delphi ships 100 times a day with its Python backend on Vercel
Gemini 3.8 Live models now available on AI Gateway
AI SDK harness layer now supports native subscription authentication