AI Chat Agent with SERP & Wikipedia Tools

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "a8211c61-5ca5-4b0a-adce-b7954a387aba",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -540,
        900
      ],
      "parameters": {
        "width": 300,
        "height": 225,
        "content": "### The conversation history (last 20 messages) is stored in a buffer memory"
      },
      "typeVersion": 1
    },
    {
      "id": "639ef27d-3e6e-4d2b-804a-5d1c95d509fc",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -200,
        900
      ],
      "parameters": {
        "width": 340,
        "height": 225,
        "content": "### Tools which agent can use to accomplish the task"
      },
      "typeVersion": 1
    },
    {
      "id": "dcb7ade3-005c-44e3-a369-526baa5b8813",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -500,
        500
      ],
      "parameters": {
        "width": 422,
        "height": 211,
        "content": "### Conversational agent will utilise available tools to answer the prompt. "
      },
      "typeVersion": 1
    },
    {
      "id": "2830de15-bdd2-48f4-8957-659014cd0a82",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -800,
        580
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "bd1865fc-c37f-4b81-8ee1-83205e67e42b",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -720,
        1000
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "d9ee6da6-f2cd-4077-913c-9215433dfc31",
      "name": "Simple Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -440,
        1000
      ],
      "parameters": {
        "contextWindowLength": 20
      },
      "typeVersion": 1.3
    },
    {
      "id": "fe8ddba3-37ba-43c3-9797-021b14a1be49",
      "name": "SerpAPI",
      "type": "@n8n/n8n-nodes-langchain.toolSerpApi",
      "position": [
        -140,
        1000
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "serpApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "f7cee7ea-6a21-4eae-a1c6-36716683a3eb",
      "name": "Wikipedia",
      "type": "@n8n/n8n-nodes-langchain.toolWikipedia",
      "position": [
        0,
        1000
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "e6f6fe48-3ad0-4bfe-a2f2-922e4c652306",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -420,
        580
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.8
    }
  ],
  "connections": {
    "SerpAPI": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Wikipedia": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• openAiApi
• serpApi

About this workflow

Stickynote. Uses stickyNote, chatTrigger, lmChatOpenAi, memoryBufferWindow. Chat trigger; 9 nodes.

Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.