Academy
⌘K
Getting Started
  • Platform Overview
  • AWS Marketplace Setup
  • Quickstart Guide
Connections
  • Overview
Workflow Builder
  • Overview
  • Nodes Catalog
Helix AI Assistant
  • Overview
Mapping Engine
  • Overview
Workflow Library
  • Overview
  • HL7
  • FHIR
  • Insurance
  • Agentic
  • Mapping
Security & Infrastructure
  • Architecture
  • HIPAA Compliance
  • Performance & Scalability
← Back to ConnectHealth
Get Started
Back to Nodes
AI Agent1 input → 1 output

AI Memory (File)

payload (object |…)topic (string)AI AgentAI Memory (File)payload (object |…)aimemory (object)Data flowProperty

Stores AI conversation memories persistently in a JSON file. Memories survive Node-RED restarts.

Inputs

payload object | string
The message to store in memory
topic string
Memory operation: "store", "search", "count", or empty for get-all

Outputs

payload object | string
Original message with memory context applied
aimemory object
Memory context for AI Agent: {context: [...], maxItems}

Details

File Memory persists conversation history to disk, allowing the AI to remember context across sessions.

Configuration

Filename
JSON file name (stored in Node-RED user directory). Default: ai-memories.json

Usage with AI Agent

Connect this node before AI Agent to provide conversation context:

[Input] → [Memory File] → [AI Agent] → [Output]

Operations

Store (topic: "store")
Saves the message to the file
Search (topic: "search")
Searches memories by content
Count (topic: "count")
Returns memory count
Get All (no topic)
Returns all stored memories

Examples

Store Memory:

msg.topic = "store";
msg.payload = {
  content: "User prefers morning appointments",
  type: "preference"
};

Best Practices

  • Use for long-term conversation context
  • Implement cleanup logic to prevent unbounded growth
  • Consider privacy implications of stored data
  • Back up memory files for production