Durable Execution

Pydantic AI allows you to build durable agents that can preserve their progress across transient API failures and application errors or restarts, and handle long-running, asynchronous, and human-in-the-loop workflows with production-grade reliability. Durable agents have full support for streaming and MCP, with the added benefit of fault tolerance.

Durability is not storage

A durable engine keeps one run alive across crashes and restarts. It does not store your chat threads: saving a conversation and picking it up later is a different problem with a much lighter answer, laid out in Persistence.

Pydantic AI supports eight durable execution solutions, plus a builder for any other engine. Five are co-maintained by the Pydantic and vendor teams:

• Temporal
• DBOS
• Prefect
• Restate
• AWS Lambda

Additional external SDK integrations:

• Kitaru
• Apache Airflow
• Absurd

One durable execution engine per agent

Each engine wraps every model request and tool call as its own durable unit, so attaching a second one, whether to the agent, for a single run, or through an agent spec, raises a UserError before either is bound.

Capability authors can also move custom hook work into engine activities, steps, or tasks with durable capability operations.

Third-party runtime authors can use the stable durable execution backend builder to integrate another engine without importing Pydantic AI internals.