Chat Memory Manager

Node catalog Artificial intelligence
On this page

Load and save chat sessions

Usage and specifics

sessionKey separates conversations; maxMessages bounds history. Select read, append or clear. Redis and PostgreSQL variants need connections; simple memory and the manager use the nodulz database.

Technical type : ai_chat_memory_manager. Runtime : nodulz.

Credentials and prerequisites

This node defines no dedicated external credential. Remote sources or execution targets may still need their own access credentials.

See the credentials guide if a remote source or execution target requires access.

Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

Parameter Type Default Values / limits
operation enum "append" load, save, clear, append
sessionKey string "default" -
sessionScope enum "workflow" workflow, shared
varKey string "ai_memory" -
role enum "user" user, assistant, system
content string "" -
maxMessages number 20 -; ≥ 1, ≤ 10000
credentialId string - -

Configuration help

operation
Operation
Load, save, append, or clear conversation history.
sessionScope
Conversation scope
Workflow scope isolates conversations by workflow and memory node. Shared scope reuses the key across workflows belonging to the same owner. New memories are isolated by default.
sessionKey
Session key
Identifies a conversation session (multiple agents can share).
varKey
Workflow variable
Workflow variable where history is stored or read.
role
Message role
Role of the appended message (user, assistant, system).
content
Content
Message content to add to memory.
maxMessages
Max messages
Maximum number of messages kept in history.
credentialId
Credential
Credential required to access the external service.

Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

json
{
  "operation": "append",
  "sessionKey": "default",
  "sessionScope": "workflow",
  "varKey": "ai_memory",
  "role": "user",
  "content": "",
  "maxMessages": 20
}

Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.

See also : Expressions and data, Executions, Node catalog.