Agent Frameworks Integration
What separates responsibilities between my agent framework and Catalyst?
Your chosen agent framework owns core orchestration, tool calling, and prompt logic, while Catalyst handles durable execution and state persistence. Catalyst wraps your framework’s execution flow via Dapr integrations, managing checkpoints, retries, and long-running pauses without altering your framework’s native behavior. Do not rely on Catalyst to replace framework-specific error handling for non-durable workflow issues.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Agent Frameworks Integration
How do I split responsibilities between my agent framework and durable execution layer?
Clarify the distinct roles between your existing agent framework and Catalyst’s durable execution layer to avoid overlapping work
- Agent Frameworks Integration
How does Catalyst manage checkpointing for production agent workflows?
Diagrid Catalyst’s checkpointing for production AI agent workflows uses Dapr’s storage to persist critical state, tool results, and conversation history.
- Agent Frameworks Integration
How do long-running human-in-the-loop agent pauses function with Catalyst?
Understand how Catalyst preserves agent workflow state during human-in-the-loop pauses, even after underlying processes terminate