Give your website or helpdesk a smart chat agent that remembers the conversation. It can greet someone, remember their name, and answer follow up questions in the same session. Ideal for customer support teams that want fast and consistent answers without adding more staff.

Here is how it works. A public chat trigger captures each message. A simple memory block keeps the last 20 messages per session using a session ID. The OpenAI Assistant creates the reply using the live chat input and the stored context. A built in calculator tool helps the bot handle numbers and quick math. The result is a chat that understands context, handles follow ups, and gives clear answers in one place.

You only need an OpenAI account and an Assistant ID. Add your OpenAI API key in n8n, set the Assistant ID in the node, and keep the memory settings as provided. Expect faster replies on common questions and fewer repeated details from users. Good fits include FAQ support, pricing and quote checks with math, and internal help for simple IT or HR questions.

• Public chat trigger that receives messages and starts a session for each user
• Simple memory stores the last 20 messages per session for context
• OpenAI Assistant generates answers using your Assistant ID and chat input
• Calculator tool lets the assistant solve numeric questions and quick estimates
• Session key mapping ties messages to the right conversation automatically
• Option to load previous session context so follow ups feel natural

• Reduce repetitive replies by up to 50 percent with a context aware chat agent
• Handle up to 5 times more chat volume without extra staff
• Cut average response time to under one minute for common questions
• Keep details like names and preferences in session to avoid repeated questions
• Give instant and accurate math answers with the built in calculator tool

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with OpenAI. See the Tools Required section above for links to create accounts with these services.
3. In your OpenAI account, create an API key from the API keys page and keep it secure.
4. In the OpenAI platform, create an Assistant and copy its Assistant ID.
5. In n8n, open the workflow and double click the OpenAI node. In the 'Credential to connect with' dropdown, click 'Create new credential' and follow the on screen instructions to add your OpenAI API key.
6. Still in the OpenAI node, paste your Assistant ID into the Assistant field and save.
7. Open the When chat message received node. Make sure Public is enabled and Load previous session is set to memory.
8. Open the Simple Memory node. Confirm the session key uses the sessionId from the chat trigger and the context window length is 20. Adjust the window if you need more or fewer messages remembered.
9. Confirm the Calculator tool node is connected to the OpenAI node as a tool. If not, connect it so the assistant can use math when needed.
10. Activate the workflow. Click Chat in the editor, send your name in the first message, then ask what your name is. The reply should include your name, which confirms memory is working.
11. If you get empty or off topic replies, check the Assistant ID and that the OpenAI credential is valid. If memory fails, verify the session key expression and that Load previous session is set to memory.