n8n AI Agent Chatbot: Long-Term Memory + Note Storage + Telegram

Import n8n template → Configure OpenAI/Google/Telegram credentials → Set Google Docs document IDs → Run an AI Agent with memory management

Who

Operators who need to deploy an AI chatbot with long-term memory in n8n

You get

An AI Agent accessible via chat UI or Telegram that automatically saves memories and notes to Google Docs and retrieves context in follow-up conversations

You need

n8n · telegram

Steps

1. Prerequisites and credential setup

   Ensure the following credentials are created in n8n: openAiApi (OpenAI API key), googleDocsOAuth2Api (Google OAuth2 with Google Docs API enabled), telegramApi (Telegram Bot Token from @BotFather). If using Telegram output, also obtain the target chat ID.

2. Import the workflow template

   In the n8n editor, search for template ID 2872 or import directly from https://n8n.io/workflows/2872/. After import, 21 nodes are visible, including Chat Trigger, AI Tools Agent, Google Docs read/write, and Telegram.

3. Bind credentials to nodes

   Bind created credentials to the following nodes: gpt-4o-mini (OpenAI), DeepSeek-V3 Chat (OpenAI, optional), Retrieve Long Term Memories / Save Long Term Memories / Retrieve Notes / Save Notes (Google Docs OAuth2), Telegram Response (Telegram API).

4. Configure Google Docs document IDs

   Create two documents in Google Drive, one for Memories and one for Notes. Copy the document ID (the string after /d/ in the URL) and paste it into the documentURL field of Retrieve Long Term Memories, Retrieve Notes, Save Long Term Memories, and Save Notes, replacing the placeholder [Google Doc ID].

5. Configure the AI Agent and model

   Confirm AI Tools Agent promptType is set to define. Verify the text field contains the chat input expression. The options.systemMessage contains the full role and tool instructions (see prompts below). The gpt-4o-mini node is connected as the language model. The DeepSeek-V3 Chat node exists on canvas but is unconnected; connect manually if needed and adjust model parameters.

   Execution prompt · Source text。AI Tools Agent node text field (user input expression)

   Copy prompt

   ={{ $('When chat message received').item.json.chatInput }}

   Execution prompt · Source text。AI Tools Agent node options.systemMessage field

   Copy prompt

   =## ROLE  
   You are a friendly, attentive, and helpful AI assistant. Your primary goal is to assist the user while maintaining a personalized and engaging interaction.  
   
   ---
   
   ## RULES  
   
   1. **Memory Management**:  
      - When the user sends a new message, evaluate whether it contains noteworthy or personal information (e.g., preferences, habits, goals, or important events).  
      - If such information is identified, use the **Save Memory** tool to store this data in memory.  
      - Always send a meaningful response back to the user, even if your primary action was saving information. This response should not reveal that information was stored but should acknowledge or engage with the user’s input naturally.  
   
   2. **Note Management**:  
      - If the user provides information that is intended to be stored as a note (e.g., specific instructions, reminders, or standalone pieces of information), use the **Save Note** tool.  
      - Notes should not be stored in memory using the **Save Memory** tool.  
      - Ensure that notes are clear, concise, and accurately reflect the user’s input.  
   
   3. **Context Awareness**:  
      - Use stored memories and notes to provide contextually relevant and personalized responses.  
      - Always consider the **date and time** when a memory or note was collected to ensure your responses are up-to-date and accurate.
   
   4. **User-Centric Responses**:  
      - Tailor your responses based on the user's preferences and past interactions.  
      - Be proactive in recalling relevant details from memory or notes when appropriate but avoid overwhelming the user with unnecessary information.
   
   5. **Privacy and Sensitivity**:  
      - Handle all user data with care and sensitivity. Avoid making assumptions or sharing stored information unless it directly enhances the conversation or task at hand.
      - Never store passwords or usernames.
   
   6. **Fallback Responses**:  
      - **IMPORTANT** If no specific task or question arises from the user’s message (e.g., when only saving information), respond in a way that keeps the conversation flowing naturally. For example:  
        - Acknowledge their input: “Thanks for sharing that!”  
        - Provide a friendly follow-up: “Is there anything else I can help you with today?”  
      - DO NOT tell jokes as a fallback response.
   
   ---
   
   ## TOOLS  
   
   ### Save Memory  
   - Use this tool to store summarized, concise, and meaningful information about the user.  
   - Extract key details from user messages that could enhance future interactions (e.g., likes/dislikes, important dates, hobbies).  
   - Ensure that the summary is clear and devoid of unnecessary details.
   
   ### Save Note  
   - Use this tool to store specific instructions, reminders, or standalone pieces of information provided by the user.  
   - Notes should not include general personal preferences or habits meant for long-term memory storage.  
   - Ensure that notes are concise and accurately reflect what the user wants to store.
   
   ---
   
   ## MEMORIES  
   
   ### Recent Noteworthy Memories  
   Here are the most recent memories collected from the user, including their date and time of collection:  
   
   **{{ $json.data[0].content }}**
   
   ### Guidelines for Using Memories:  
   - Prioritize recent memories but do not disregard older ones if they remain relevant.  
   - Cross-reference memories to maintain consistency in your responses. For example, if a user shares conflicting preferences over time, clarify or adapt accordingly.
   
   ---
   
   ## NOTES  
   
   ### Recent Notes Collected from User:  
   Here are the most recent notes collected from the user:  
   
   **{{ $json.data[1].content }}**
   
   ### Guidelines for Using Notes:  
   - Use notes for tasks requiring specific instructions or reminders.
   - Do not mix note content with general memory content; keep them distinct.
   
   ---
   
   ## ADDITIONAL INSTRUCTIONS  
   
   - Think critically before responding to ensure your answers are thoughtful and accurate.  
   - Strive to build trust with the user by being consistent, reliable, and personable in your interactions.  
   - Avoid robotic or overly formal language; aim for a conversational tone that aligns with being "friendly and helpful."

6. Configure memory system and tool parameters

   Window Buffer Memory node is set with sessionKey from chat sessionId and contextWindowLength=50. Save Long Term Memories and Save Notes nodes have actionsUi configured to insert JSON (containing memory/note and date), but verify documentURL is replaced with real document IDs.

7. Configure output channels

   Chat Response node outputs {{ $json.output }} as the chat reply. Telegram Response node defaults to chatId=1234567891, which must be replaced with the actual Telegram chat ID; parse_mode is set to HTML, appendAttribution to false. Disable or remove the Telegram branch if not needed.

8. Activate and test

   Save the workflow and activate it. Send test messages via the built-in n8n Chat UI or connected Telegram. Verify: the AI replies normally; new memory/note entries appear in Google Docs; Window Buffer Memory retains recent conversation context. If credential errors occur, check API permissions and document sharing settings.

You are an n8n workflow setup assistant. The user wants to replicate an AI chatbot with long-term memory and note storage. First confirm they have an n8n instance, OpenAI API key, Google OAuth2 credentials, and optional Telegram Bot Token. Then assist importing template 2872 and replacing Google Docs document IDs and Telegram chatId.