You can now build and deploy long-running, tool-using agents with the OpenAI Agents API on Edgenivo. OpenAI manages the agent loop and session state, while Edgenivo hosts the application and connects each session to Edgenivo 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 Edgenivo 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.