This n8n workflow orchestrates a sophisticated chat memory management system integrated with OpenAI’s language model to facilitate dynamic and context-aware conversations. It enables users to interact with an AI assistant that remembers previous chat sessions, providing continuity and personalized responses.

The workflow begins with a webhook trigger (‘Chat Trigger’) that initiates the process when a user sends a message. It retrieves conversation history stored in memory (‘Chat Memory Manager’ and ‘Chat Memory Manager1’), both of which handle stored chat sessions. Sticky notes are used as visual annotations within the workflow to document each step for easy understanding.

The system reads the previous chat content from memory, then constructs a prompt combining past messages with the current user input. This prompt is sent to the ‘OpenAI Assistant’ node, which processes it and generates a response. The latest conversation exchange is added back into memory to keep the chat context current (

thanks to the ‘Chat Memory Manager1’ node)

A ‘Limit’ node constrains the output data to ensure clean responses. The entire process allows for continuous, multi-turn conversations by maintaining context through a buffer (‘Window Buffer Memory’) that temporarily stores recent chat exchanges. Finally, the assistant’s reply is returned to the user, making this an effective setup for creating interactive, context-aware chatbots on WordPress or other platforms.

Practically, this workflow is ideal for deploying intelligent chatbots that require session continuity, such as customer support bots, personal assistants, or conversational interfaces on websites.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.memoryBufferWindow, @n8n/n8n-nodes-langchain.memoryManager, @n8n/n8n-nodes-langchain.openAiAssistant, @n8n/n8n-nodes-langchain.toolCalculator, aggregate, limit, set, stickyNote