What it does
A framework for building resilient stateful agents with explicit graphs, persistence, human-in-the-loop flows, and controllable execution.
Why it belongs here
Stateful graphs help keep agents from wandering through expensive loops. Fewer accidental tool calls, more deliberate context.
Best use case
Agent workflows that need explicit state, resumability, human review, branching, and clearer control over multi-step execution.
How to use it
Model the workflow as a graph, add stopping rules and review nodes, and log each model and tool step as part of the agent trace.
Limits
A graph can make behavior easier to inspect, but it does not make every task a good fit for agent automation.
Tags
agentsstateworkflows
