Durable Execution

Use durable execution in production when a run in flight has to survive its process stopping, through a deploy, a crash or a transient API failure, or when a workflow waits hours or days for a person or another system. A durable engine journals the agent’s model requests and the tool calls it wraps, and a restarted run replays the completed ones from the journal and retries the one in flight. Which tool calls (function tools, MCP servers) an engine wraps for you and how it delivers streaming differ per engine; each page below says.

Durability is not storage

A durable engine keeps one run alive when it crashes partway through a step, with retries and journaled model and tool calls. Saving a run, resuming it later and forking it from an earlier step need no engine: StepPersistence from Pydantic AI Harness snapshots every settled step to a store you choose, the way a checkpointer does, and Persistence lays out the options.

Pydantic AI supports eight durable execution engines, plus a builder for any other engine. Each page below has a complete example:

Engine	Install	Make an agent durable with
Temporal	pydantic-ai-slim[temporal]	TemporalDurability from pydantic_ai.durable_exec.temporal
DBOS	pydantic-ai-slim[dbos]	DBOSDurability from pydantic_ai.durable_exec.dbos
Prefect	pydantic-ai-slim[prefect]	PrefectDurability from pydantic_ai.durable_exec.prefect
Restate	restate_sdk[serde]	RestateAgent from restate.ext.pydantic
AWS Lambda	pydantic-ai-harness[aws-lambda]	AWSLambdaDurability from pydantic_ai_harness.aws_lambda
Absurd	pydantic-ai-harness[absurd]	AbsurdDurability from pydantic_ai_harness.absurd
pgtask	pydantic-ai-harness[pgtask]	PGTaskDurability from pydantic_ai_harness.pgtask
Apache Airflow	apache-airflow-providers-common-ai	AgentOperator(..., durable=True) from airflow.providers.common.ai.operators.agent

Temporal, DBOS, Prefect, Restate, and AWS Lambda are co-maintained by the Pydantic and vendor teams. AWS Lambda, Absurd, and pgtask ship in Pydantic AI Harness; Restate and Airflow ship in the engine’s own package.

One durable execution engine per agent

Each engine journals the model requests and the tool calls it wraps as its own durable units, 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.

Append-on-change instructions derive their baseline and replacements from persisted history. Instruction callbacks still follow the engine’s replay rules: use a durable operation for external reads so replay uses the same values and produces the same history shape.

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

Harness workspace capabilities such as Coder, Shell, and FileSystem also run inside a durable agent; the workspace guide shows how, and what works on each engine.