Letta Webhook Chat API

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 →

{
  "name": "Letta Webhook Chat API",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "letta-chat",
        "responseMode": "responseNode",
        "options": {}
      },
      "id": "1a2b3c4d-5e6f-7a8b-9c0d-1e2f3a4b5c6d",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        250,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Extract message and agent ID from webhook payload\nconst body = $input.item.json.body || {};\n\nreturn {\n  agentId: body.agentId || body.agent_id,\n  message: body.message,\n  role: body.role || 'user'\n};"
      },
      "id": "2b3c4d5e-6f7a-8b9c-0d1e-2f3a4b5c6d7e",
      "name": "Extract Input",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        470,
        300
      ]
    },
    {
      "parameters": {
        "operation": "sendMessage",
        "agentId": "={{ $json.agentId }}",
        "role": "={{ $json.role }}",
        "message": "={{ $json.message }}",
        "additionalOptions": {
          "max_steps": 10,
          "use_assistant_message": true
        }
      },
      "id": "3c4d5e6f-7a8b-9c0d-1e2f-3a4b5c6d7e8f",
      "name": "Letta",
      "type": "@letta-ai/n8n-nodes-letta.letta",
      "typeVersion": 1,
      "position": [
        690,
        300
      ],
      "credentials": {
        "lettaApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "// Format the response for the API consumer\nconst messages = $input.item.json.messages || [];\nconst assistantMessages = messages.filter(msg => msg.role === 'assistant');\n\nreturn {\n  success: true,\n  response: assistantMessages.map(msg => msg.text || msg.content).join('\\n'),\n  messages: assistantMessages,\n  usage: $input.item.json.usage\n};"
      },
      "id": "4d5e6f7a-8b9c-0d1e-2f3a-4b5c6d7e8f9a",
      "name": "Format Response",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        910,
        300
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ $json }}",
        "options": {
          "responseHeaders": {
            "entries": [
              {
                "name": "Content-Type",
                "value": "application/json"
              }
            ]
          }
        }
      },
      "id": "5e6f7a8b-9c0d-1e2f-3a4b-5c6d7e8f9a0b",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1130,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Handle errors gracefully\nconst error = $input.item.json.error || 'Unknown error';\n\nreturn {\n  success: false,\n  error: error.message || error\n};"
      },
      "id": "6f7a8b9c-0d1e-2f3a-4b5c-6d7e8f9a0b1c",
      "name": "Error Handler",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        910,
        480
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ $json }}",
        "options": {
          "responseCode": 500,
          "responseHeaders": {
            "entries": [
              {
                "name": "Content-Type",
                "value": "application/json"
              }
            ]
          }
        }
      },
      "id": "7a8b9c0d-1e2f-3a4b-5c6d-7e8f9a0b1c2d",
      "name": "Error Response",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1130,
        480
      ]
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Extract Input",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Input": {
      "main": [
        [
          {
            "node": "Letta",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Letta": {
      "main": [
        [
          {
            "node": "Format Response",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Error Handler",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Response": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Error Handler": {
      "main": [
        [
          {
            "node": "Error Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [],
  "triggerCount": 0,
  "updatedAt": "2025-01-07T00:00:00.000Z",
  "versionId": "1"
}

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.

• lettaApi

About this workflow

Letta Webhook Chat API. Uses @letta-ai/n8n-nodes-letta. Webhook trigger; 7 nodes.

Source: https://github.com/letta-ai/n8n-nodes-letta/blob/6cf2d1da050c4c0deb9f2a57273f91721cef4936/demo/workflows/webhook-chat.json — original creator credit. Request a take-down →

More General workflows → · Browse all categories →

Related workflows

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