Agent Memory & State
What’s the safest way to purge stale agent conversation memory?
The safest way to purge stale AI agent conversation memory is to only remove non-replayable memory outside Catalyst’s durable execution checkpoints. Catalyst retains replayable workflow state to support reliable crash recovery, so offload non-critical conversation data to a dedicated vector or object store for long-term retention rather than deleting it directly. Avoid purging state tied to in-flight workflow checkpoints, as this breaks the platform’s core replay functionality for active workflows.
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.