DBOS and Databricks partner in order to help you build agents that are reliable and reproducible by default. The integration layers DBOS, a lightweight database-backed durable execution library, directly underneath your agents, adding fault tolerance and observability that runs entirely on your existing Databricks infrastructure. With DBOS, teams can orchestrate AI workflows, long-running pipelines, preserve state across failures, and build reliable, production-grade applications on top of lakehouse data.
Because DBOS is a lightweight library built on Postgres, you can easily add it to your existing Databricks-hosted agents. This demo on GitHub shows you how to add DBOS to a Databricks-hosted agent built with the OpenAI Agents SDK.
