Getting Started & Migration
How do I iterate quickly on durable agent logic without deploying to a shared cluster?
Catalyst runs fully on your machine via a local Dapr sidecar, allowing you to execute and debug agent workflows without remote infrastructure. You can simulate failures, inspect state transitions, and verify deterministic replay after code changes. A tight edit-run-debug cycle is possible because workflow state is stored locally. Boundary: State storage is ephemeral by default; persistent state requires an external store for production realism.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Getting Started & Migration
What does a minimal but realistic durable agent look like when I first run Catalyst locally?
A realistic durable agent prototype that progresses from a call to an LLM through a conditional action to an API, illustrating automatic state persistence.
- Getting Started & Migration
My agent is already built with LangChain/LlamaIndex. Can I add durable execution without a rewrite?
Wrap an existing agent’s entry point in a Catalyst workflow to gain durability without modifying framework internals, then progressively refactor.
- Getting Started & Migration
Which agent workflows should I migrate to Catalyst first to gain the most value?
Identify workflows where partial failures cause expensive manual recovery or data inconsistency to prioritize for durable execution migration.