Skip to content

n8n

deployment

services:
  postgres:
    image: postgres:16-alpine
    restart: unless-stopped
    environment:
      - POSTGRES_USER=n8n
      - POSTGRES_PASSWORD=foo@123
      - POSTGRES_DB=n8n
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U n8n"]
      interval: 10s
      timeout: 5s
      retries: 5

  redis:  # Keep Redis if you want it for future use, but not required now
    image: redis:7-alpine
    restart: unless-stopped
    command: redis-server --appendonly yes
    volumes:
      - redis_data:/data

  n8n:
    image: docker.n8n.io/n8nio/n8n:latest
    restart: unless-stopped
    ports:
      - "5678:5678"
    environment:
      - DB_TYPE=postgresdb
      - DB_POSTGRESDB_HOST=postgres
      - DB_POSTGRESDB_PORT=5432
      - DB_POSTGRESDB_DATABASE=n8n
      - DB_POSTGRESDB_USER=n8n
      - DB_POSTGRESDB_PASSWORD=foo@123

      - N8N_HOST=0.0.0.0
      - N8N_PORT=5678
      - N8N_PROTOCOL=http
      # Required for HTTP / non-localhost URLs; use HTTPS in production and omit or set true
      - N8N_SECURE_COOKIE=false
      # WEBHOOK_URL=http://your-domain-or-ip:5678/
      - WEBHOOK_URL=http://x.x.x.x:5678/

      - GENERIC_TIMEZONE=America/Chicago
      - TZ=America/Chicago

      # Disable runners/queue mode for stability with AI Agents + Chat Trigger
      - N8N_RUNNERS_ENABLED=false
      - EXECUTIONS_MODE=regular

      # Increase timeout for AI + Redfish calls
      - EXECUTIONS_TIMEOUT=600
      - EXECUTIONS_TIMEOUT_MAX=7200
    volumes:
      - n8n_data:/home/node/.n8n
    depends_on:
      postgres:
        condition: service_healthy

volumes:
  postgres_data:
  redis_data:
  n8n_data:

with local vllm which can reference the LLM to Agent RTX 5070 can use the nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8 

services:
  vllm:
    image: vllm/vllm-openai:latest
    container_name: vllm
    restart: unless-stopped
    runtime: nvidia
    ipc: host
    ports:
      - "8000:8000"
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    command: >
      --model nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8
      --enable-auto-tool-choice
      --tool-call-parser qwen3_coder
      --reasoning-parser nemotron_v3
      --max-model-len 32768
      --max-num-seqs 1
      --trust-remote-code
      --gpu-memory-utilization 0.85
      --kv-cache-dtype fp8
      --host 0.0.0.0

template

AI Agent for Localhost

{
  "name": "AI Agent for Localhost",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        0,
        0
      ],
      "id": "f1a5dcfc-2838-44a3-8c4d-ae37c64312c6",
      "name": "When chat message received",
      "webhookId": "4b172f66-ad5c-4ccf-944b-b44e9a07217b"
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are an AI Linux System Administrator Agent expert designed to help manage Linux systems.\nThe user will communicate with you as a fellow colleague. You must understand their final intention and act accordingly.\nYou can execute single-line bash commands inside a Linux System using the SSH tool.\nTo pass a command to execute, you should only pass the command itself.\nReplacing null with a command you want to execute.\n\n\nYour objectives are:\n\n### 1. Understand User Intent\n- Parse user requests related to Linux operations.\n- Accurately interpret the intent to generate valid Linux commands.\n- Accurately interpret the response you receive from a Linux System.\n- Provide the user with an interpreted response.\n\n### 2. Refer to tools\n- Execute SSH\n\n### 3. Restrictions\n- Do not do destructive actions without confirmation from the user.\n- Under no circumstance execute \"rm -rf\" command.\n\n### 4. Behavior Guidelines\n- Be concise, precise, and consistent.\n- Ensure all generated commands are compatible with Linux SSH.\n- Rely on system defaults when user input is incomplete.\n- For unknown or unrelated queries, clearly indicate invalid input.\n- when stderr contain \"command not found\", try to install the missing package after user's confirmation",
          "maxIterations": 30
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        208,
        0
      ],
      "id": "b24d122f-ec61-44bb-b018-b77661dfe90b",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8",
          "mode": "list",
          "cachedResultName": "nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8"
        },
        "builtInTools": {},
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.3,
      "position": [
        80,
        208
      ],
      "id": "b914f89e-392c-49e0-8d49-143b3755ef4e",
      "name": "OpenAI Chat Model",
      "credentials": {
        "openAiApi": {
          "id": "ahoGALlM1ZkXbVWu",
          "name": "OpenAI account"
        }
      }
    },
    {
      "parameters": {
        "description": "Execute shell commands on the remote Linux host via SSH",
        "source": "parameter",
        "workflowJson": "{\n  \"nodes\": [\n    {\n      \"parameters\": {\n        \"workflowInputs\": {\n          \"values\": [\n            {\n              \"name\": \"query\"\n            }\n          ]\n        }\n      },\n      \"type\": \"n8n-nodes-base.executeWorkflowTrigger\",\n      \"typeVersion\": 1.1,\n      \"position\": [\n        0,\n        0\n      ],\n      \"id\": \"29e380c2-2ecd-465e-a784-f31b1c204b38\",\n      \"name\": \"When Executed by Another Workflow\"\n    },\n    {\n      \"parameters\": {\n        \"command\": \"=export PATH=$PATH:/usr/bin:/usr/lib/wsl/lib; {{ $json.query }}\"\n      },\n      \"type\": \"n8n-nodes-base.ssh\",\n      \"typeVersion\": 1,\n      \"position\": [\n        220,\n        0\n      ],\n      \"id\": \"81a147e8-e8c8-4c98-8a9b-24de4e0152a0\",\n      \"name\": \"SSH\",\n      \"alwaysOutputData\": true,\n      \"credentials\": {\n        \"sshPassword\": {\n          \"id\": \"JkHcZoevDfZRWlUK\",\n          \"name\": \"SSH Password account\"\n        }\n      },\n      \"onError\": \"continueErrorOutput\"\n    }\n  ],\n  \"pinData\": {},\n  \"connections\": {\n    \"When Executed by Another Workflow\": {\n      \"main\": [\n        [\n          {\n            \"node\": \"SSH\",\n            \"type\": \"main\",\n            \"index\": 0\n          }\n        ]\n      ]\n    }\n  }\n}\n\n\n\n\n\n\n\n\n"
      },
      "type": "@n8n/n8n-nodes-langchain.toolWorkflow",
      "typeVersion": 2.2,
      "position": [
        512,
        208
      ],
      "id": "f78edeea-2c50-4312-9232-83565bcff328",
      "name": "Execute SSH"
    }
  ],
  "pinData": {},
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Execute SSH": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate"
  },
  "versionId": "1af5079a-b054-4118-af60-52796bdc77fd",
  "meta": {
    "templateCredsSetupCompleted": true,
    "instanceId": "e1acf573e6487637a947a14a16d366d3933d7118d3a97a8d73d0ffc0cc3e79b6"
  },
  "id": "v4y8vBMqBTfvmQ69",
  "tags": []
}

AI agent with Built-in SSH Node

{
  "name": "AI agent with Built-in SSH Node",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        0,
        0
      ],
      "id": "01f3a6df-ada9-489b-8901-5a7cc1d13c17",
      "name": "When chat message received",
      "webhookId": "e54d9053-6e43-48cc-9cf7-3fa6f82f155f"
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are an expert Linux  administrator. Your ONLY goal is to run the commands on the remote host via SSH.\n\nYou have access to the 'Build-in SSH node' tool. Use it for every action on the remote host.\n\nThe tool returns stdout, stderr, and exit code.\n\nSTRICT RULES:\n- Work in clear, sequential steps. After each major step, summarize what you did and what the output was.\n- Never run more than one long command per tool call unless necessary.\n- If a command takes >30 seconds, use `timeout` or run it with `nohup` + background if appropriate, but prefer simple blocking commands first.\n- If anything fails, report the exact error and ask for clarification.\n\nAlways be concise in your reasoning."
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        208,
        0
      ],
      "id": "a8677c2e-57ba-4b6b-87b6-f8d57ba25c2c",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "model": "grok-4-1-fast-reasoning",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatXAiGrok",
      "typeVersion": 1,
      "position": [
        80,
        208
      ],
      "id": "e76bc58e-d631-4b12-a952-45d8da60e81b",
      "name": "xAI Grok Chat Model",
      "credentials": {
        "xAiApi": {
          "id": "dVr2LJqB2QduwKrH",
          "name": "xAi account"
        }
      }
    },
    {
      "parameters": {
        "source": "parameter",
        "workflowJson": "\n{\n  \"nodes\": [\n    {\n      \"parameters\": {\n        \"workflowInputs\": {\n          \"values\": [\n            {\n              \"name\": \"query\"\n            }\n          ]\n        }\n      },\n      \"type\": \"n8n-nodes-base.executeWorkflowTrigger\",\n      \"typeVersion\": 1.1,\n      \"position\": [\n        0,\n        0\n      ],\n      \"id\": \"29e380c2-2ecd-465e-a784-f31b1c204b38\",\n      \"name\": \"When Executed by Another Workflow\"\n    },\n    {\n      \"parameters\": {\n        \"command\": \"={{ $json.query }}\"\n      },\n      \"type\": \"n8n-nodes-base.ssh\",\n      \"typeVersion\": 1,\n      \"position\": [\n        220,\n        0\n      ],\n      \"id\": \"81a147e8-e8c8-4c98-8a9b-24de4e0152a0\",\n      \"name\": \"SSH\",\n      \"alwaysOutputData\": true,\n      \"credentials\": {\n        \"sshPassword\": {\n          \"id\": \"xjZ8fdwnMvlGYUTI\",\n          \"name\": \"SSH Password account\"\n        }\n      },\n      \"onError\": \"continueErrorOutput\"\n    }\n  ],\n  \"pinData\": {},\n  \"connections\": {\n    \"When Executed by Another Workflow\": {\n      \"main\": [\n        [\n          {\n            \"node\": \"SSH\",\n            \"type\": \"main\",\n            \"index\": 0\n          }\n        ]\n      ]\n    }\n  }\n}\n\n\n\n\n\n\n\n"
      },
      "type": "@n8n/n8n-nodes-langchain.toolWorkflow",
      "typeVersion": 2.2,
      "position": [
        496,
        176
      ],
      "id": "d33bb4e1-2ac7-4fdc-9ade-a054bd449323",
      "name": "Call 'Build-in SSH node'"
    }
  ],
  "pinData": {},
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "xAI Grok Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Call 'Build-in SSH node'": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate"
  },
  "versionId": "f8f9e4f3-443f-4392-ae95-01ae6396e3d0",
  "meta": {
    "instanceId": "99e5fc265fd8b35bcde7b27ef921b9989b8800054116f489a219d4ecb60c07ec"
  },
  "id": "923yW4EpCTW3s248",
  "tags": []
}

AI agent with Community SSH Node

prerequisite Install the Comminuty Node: n8n-nodes-sshv2

{
  "name": "AI agent with Community SSH Node",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        0,
        0
      ],
      "id": "70766e77-48e0-4b8c-a9a0-06e13f4d2bd6",
      "name": "When chat message received",
      "webhookId": "074248bf-10cb-44b3-946f-a53eba55cf84"
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are an expert Linux  administrator. Your ONLY goal is to run the commands on the remote host via SSH.\n\nYou have access to the 'build-in ssh node' tool. Use it for every action on the remote host.\n\nIf basic commands fail to show output, use: bash -l -c 'your command here'\nThe tool returns stdout, stderr, and exit code.\n\nSTRICT RULES:\n- Work in clear, sequential steps. After each major step, summarize what you did and what the output was.\n- Never run more than one long command per tool call unless necessary.\n- If a command takes >30 seconds, use `timeout` or run it with `nohup` + background if appropriate, but prefer simple blocking commands first.\n- If anything fails, report the exact error and ask for clarification.\n\nAlways be concise in your reasoning."
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        208,
        0
      ],
      "id": "5513a9fb-23af-4736-ac6f-1ee51be14663",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "model": "grok-4-1-fast-reasoning",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatXAiGrok",
      "typeVersion": 1,
      "position": [
        80,
        208
      ],
      "id": "283accd0-f233-40e6-9af2-2803e27390d4",
      "name": "xAI Grok Chat Model",
      "credentials": {
        "xAiApi": {
          "id": "dVr2LJqB2QduwKrH",
          "name": "xAi account"
        }
      }
    },
    {
      "parameters": {
        "connectionType": "credentials",
        "command": "={{ $fromAI('Command', ``, 'string') }}",
        "workingDirectory": "/"
      },
      "type": "n8n-nodes-sshv2.hadidizAiTool",
      "typeVersion": 1,
      "position": [
        528,
        208
      ],
      "id": "ad18e3ef-da10-4e3b-8318-a6c600681f54",
      "name": "Hadidiz-AI",
      "credentials": {
        "sshPasswordApi": {
          "id": "Pf8Dy7wI5qIv2ITR",
          "name": "SSH Password account 2"
        }
      }
    }
  ],
  "pinData": {},
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "xAI Grok Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Hadidiz-AI": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "versionId": "04982771-db19-48a6-8ce5-529ae9eab8f2",
  "meta": {
    "templateCredsSetupCompleted": true,
    "instanceId": "99e5fc265fd8b35bcde7b27ef921b9989b8800054116f489a219d4ecb60c07ec"
  },
  "id": "ipOa1KLsLSFQAdT2",
  "tags": []
}