@RichardCray re-reading happens because your memory node dumps the full chat history into context every turn. Swap to Window Buffer Memory with contextWindowLength: 5 so only the last 5 messages replay. Wire it into the AI Agent’s aimemory input alongside your OpenAI Chat Model node. Then add a systemMessage like “Respond only to the latest patient message, do not summarize prior turns” — that stops it re-analyzing previous turns.
achamm
6
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| AgentMem — Your AI agents stop repeating mistakes (memory + event bridge) | 6 | 93 | May 26, 2026 | |
| How to maintain conversation context/memory with AI Agent for follow-up questions? | 2 | 1958 | June 9, 2026 | |
| I am building an ai agent in n8n and i am stuck | 3 | 123 | September 2, 2025 | |
| [Help Request] AI Agent in n8n — How to Achieve a Fully Conversational, Multi-Turn Flow? | 3 | 1242 | January 20, 2026 | |
| Re-running an AI agent more than once - conditionally | 6 | 2008 | November 16, 2024 |