Persistent Chat Memory
Persistent Chat Memory
Section titled “Persistent Chat Memory”Chat memory persisted across runs and workflows under a named conversation key
What it does
Section titled “What it does”Maintains conversation history that persists across separate workflow runs, keyed off a conversation key you choose. Any two executions — in this workflow or another — that use the same key share the same persisted memory.
When to use it
Section titled “When to use it”Connect this to AI agents that need to remember context across multiple, separate executions of a workflow (not just within a single run), such as a long-running support bot thread. Unlike Local Memory, the conversation key is meant to be set explicitly rather than wired dynamically.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Conversation Key | A stable, user-chosen identifier used to persist this memory across runs. Placeholder: e.g. support-bot-main-thread. Required — the node throws an error if left empty. |
Outputs
Section titled “Outputs”Returns a memory dependency for conversational AI workflows.
Dependencies and credentials
Section titled “Dependencies and credentials”- No explicit credential dependency is declared in the node description.
Example workflow
Section titled “Example workflow”Connect Persistent Chat Memory to an AI agent or dependency input that accepts this dependency type, set a stable Conversation Key, then run the agent with data from previous nodes. Reuse the same key in a later run to continue the same conversation.
Troubleshooting
Section titled “Troubleshooting”- Check that Conversation Key is set — the node throws an error if it is empty.
- Using a different Conversation Key starts a fresh, unrelated memory; reuse the exact same key to continue a prior conversation.
- No dedicated source test was found next to this node; verify behavior manually when changing this page.