Agent Memory & State
Where should I store agent conversation history for long-running workflows?
Store long-running agent conversation history outside Catalyst’s durable execution core state. Catalyst only tracks critical workflow progression state, so you can fetch conversation history from production-grade specialized external storage when needed for your agent’s LLM context prompts, requiring reliable external access to avoid critical workflow disruptions. Avoid storing non-critical transient session data directly in Catalyst’s core state store to prevent unnecessary state bloat that impacts execution performance.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Agent Memory & State
How do workflow state, conversation memory, and retrieval corpora differ for AI agents?
Explain how workflow state, conversation memory, and retrieval corpora differ for AI agents, including their unique roles in durable execution systems.
- Agent Memory & State
Which agent memory and state should be included in durable execution?
Outline which types of agent memory and state are appropriate for inclusion in durable execution layers for production AI agent workloads.
- Agent Memory & State
What agent state survives a workflow crash or restart?
Explain which agent state is preserved following a workflow crash or unexpected restart, and how Catalyst manages state persistence.