This workflow follows the Chainllm → OpenAI Chat recipe pattern — see all workflows that pair these two integrations.
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": "Smart Select Multi Tool Agent",
"nodes": [
{
"parameters": {
"operation": "clone",
"repositoryPath": "={{ $json.git_directory }}",
"sourceRepository": "https://github.com/danielmiessler/fabric.git"
},
"type": "n8n-nodes-base.git",
"typeVersion": 1,
"position": [
1260,
1100
],
"id": "9f7e006d-1e60-4f40-a69c-b5245d5c7551",
"name": "Clone fabric git",
"onError": "continueRegularOutput"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "2f090819-692c-4f18-818d-5084726b6e10",
"name": "git_directory",
"value": "/tmp/fabric",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1040,
1100
],
"id": "58053e19-f5cf-43ce-9432-8c620cd106b0",
"name": "set git path"
},
{
"parameters": {
"command": "=ls {{ $('set git path').item.json.git_directory }}/patterns "
},
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
1500,
1100
],
"id": "38f86a94-f784-46af-b1f5-f8a258e2f7c0",
"name": "get available prompts"
},
{
"parameters": {
"jsCode": "// Input Data (replace with the actual data input in n8n)\nconst inputString = $json[\"stdout\"];\n\n// Split the input string into lines\nconst lines = inputString.split('\\n').map(line => line.trim());\n\n// Return the list as a single item with a \"patterns\" property\nreturn [{ patterns: lines }];\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1740,
1100
],
"id": "276f1855-eb26-4ca7-bf40-fa5d7972f59f",
"name": "transform pattern list to json"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('cut first 100 characters').item.json.truncatedText }}",
"messages": {
"messageValues": [
{
"message": "=You are highly intelligent and accurate sentiment analyzer. Analyze the sentiment of the provided text. Categorize it into one of the following: {{ $json.patterns }}. Output the pattern (e.g. agility_story) and nothing else."
}
]
}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.5,
"position": [
2080,
1100
],
"id": "0526b68f-2255-475a-991e-8eb34f9e19eb",
"name": "decide what pattern should be used"
},
{
"parameters": {
"jsCode": "// n8n Function Node\nreturn items.map(item => {\n // Get the input text\n const inputText = item.json.message.content || '';\n \n // Cut the text to the first 100 characters\n const truncatedText = inputText.substring(0, 100);\n \n // Return the truncated text\n return {\n json: {\n truncatedText,\n },\n };\n});\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
800,
1100
],
"id": "0803454c-adb0-4889-a02e-fe56f9e8cb03",
"name": "cut first 100 characters"
},
{
"parameters": {
"command": "=cat {{ $('set git path').item.json.git_directory }}/patterns/{{ $json.text }}/system.md"
},
"type": "n8n-nodes-base.executeCommand",
"typeVersion": 1,
"position": [
2560,
1100
],
"id": "0d36c23f-35f2-4cc9-a81e-9565071b12e1",
"name": "get_selected_pattern_system_prompt"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "18b7c3b4-8581-44ca-a75e-324b4c7db6a5",
"name": "system_prompt",
"value": "={{ $json.stdout }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
2860,
1240
],
"id": "a152911e-06b7-4f65-93ee-49917c80acbb",
"name": "set_system_prompt"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $('Prep Input Fields').item.json.query }}",
"messages": {
"messageValues": [
{
"message": "={{ $json.system_prompt }}"
}
]
}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.5,
"position": [
240,
1520
],
"id": "907320fc-0559-405e-8209-44008c248d3c",
"name": "Run chatInput with specialized tool"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "6bf569bc-9c4a-471c-a9c7-0fb0d660de4f",
"name": "output",
"value": "=Based on the Request: {{ $('cut first 100 characters').item.json.truncatedText }}\n\nI decided to use the tool \"{{ $('decide what pattern should be used').item.json.text }}\"\n\nThis is the Result:\n{{ $json.text }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
620,
1520
],
"id": "6b3206c1-ddd1-44a3-aaa6-d9dd3927039d",
"name": "set output"
},
{
"parameters": {
"content": "## This is basically sentiment analysis but with the available categories as dynamic variables.",
"height": 360,
"width": 320,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
2040,
900
],
"id": "a0bc524c-262f-4a9c-8cf7-7927dac1f4b2",
"name": "Sticky Note5"
},
{
"parameters": {
"content": "## Tip:\nDepending on Model and Hardware you should experiment with context limit and max token lenth for respond to fin etune",
"height": 280,
"width": 420,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
1580,
1540
],
"id": "6bd0983f-1fa4-432d-8996-74daa138f920",
"name": "Sticky Note6"
},
{
"parameters": {
"content": "# This is a smart selecting Multi-Tool-Agent / Masteragent based on fabric\n\n## it decides what tool to use based on the first 100 characters of the prompt. All tools/patterns/prompts from the fabric repository are imported.\n\nSetup needs to be done manually via clicking \"Test workflow\". You may need to adjust directory and or permissions.\n\n\nList of available prompts:\nhttps://github.com/danielmiessler/fabric/tree/main/patterns\n\nGithub Repository of fabric:\nhttps://github.com/danielmiessler/fabric",
"height": 340,
"width": 2780
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
0,
0
],
"id": "4771c111-7d89-4f31-8573-2f2e185de6b1",
"name": "Sticky Note4"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
1640,
1700
],
"id": "d7869962-80ec-424c-8748-f0edaf3b7967",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
1840,
1700
],
"id": "0316b440-828b-47db-b57d-73ba78d521b3",
"name": "OpenAI Chat Model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"respondWith": "allIncomingItems",
"options": {
"responseHeaders": {
"entries": [
{
"name": "X-n8n-Signature",
"value": ""
}
]
}
}
},
"id": "32dd6495-0870-427b-9f32-a4bbe367c67a",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1340,
1520
]
},
{
"parameters": {
"tableId": "messages",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "session_id",
"fieldValue": "={{ $json.session_id }}"
},
{
"fieldId": "message",
"fieldValue": "={{ {\n\"type\": \"human\",\n\"content\": $json.query,\n\"additional_kwargs\": {},\n\"response_metadata\": {}\n} }}"
}
]
}
},
"id": "052c37ad-e9d7-4df6-848d-f3cedff4112f",
"name": "Add User Message to DB",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
560,
1100
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"tableId": "messages",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "session_id",
"fieldValue": "={{ $('Prep Input Fields').first().json.session_id }}"
},
{
"fieldId": "message",
"fieldValue": "={{ {\n\"type\": \"ai\",\n\"content\": $json.output,\n\"data\": {},\n\"additional_kwargs\": {},\n\"response_metadata\": {}\n} }}"
}
]
}
},
"id": "7df20368-6ae6-49c2-b38a-80ee3ba03dc4",
"name": "Add AI Message to DB",
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
860,
1520
],
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "ee2bcd57-3b4c-43f9-b4b7-3a25687b9a68",
"name": "query",
"value": "={{ $json.body.query }}",
"type": "string"
},
{
"id": "63f23e51-af2b-47c4-a288-5abaf9b6c357",
"name": "user_id",
"value": "={{ $json.body.user_id }}",
"type": "string"
},
{
"id": "b97a3670-8a87-481b-8695-db44624be7d8",
"name": "request_id",
"value": "={{ $json.body.request_id }}",
"type": "string"
},
{
"id": "7d3fa06d-08f7-4517-b9c5-3c46ff476f55",
"name": "session_id",
"value": "={{ $json.body.session_id }}",
"type": "string"
}
]
},
"options": {}
},
"id": "bf3d7819-97dd-4737-9950-1d301997e260",
"name": "Prep Input Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
320,
1100
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "b5eaa2a2-a6bc-40ab-af5e-baa8a5dda1a7",
"name": "success",
"value": "=true",
"type": "boolean"
}
]
},
"options": {}
},
"id": "6dde63a9-cf9b-486e-8784-fa62ea2e6a34",
"name": "Prep Output Fields",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1100,
1520
]
},
{
"parameters": {
"httpMethod": "POST",
"path": "invoke-fabric-agent",
"authentication": "headerAuth",
"responseMode": "responseNode",
"options": {}
},
"id": "3564683a-6840-4234-a260-4811df45ec07",
"name": "Webhook1",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
100,
1100
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
}
],
"connections": {
"set git path": {
"main": [
[
{
"node": "Clone fabric git",
"type": "main",
"index": 0
}
]
]
},
"get available prompts": {
"main": [
[
{
"node": "transform pattern list to json",
"type": "main",
"index": 0
}
]
]
},
"transform pattern list to json": {
"main": [
[
{
"node": "decide what pattern should be used",
"type": "main",
"index": 0
}
]
]
},
"decide what pattern should be used": {
"main": [
[
{
"node": "get_selected_pattern_system_prompt",
"type": "main",
"index": 0
}
]
]
},
"cut first 100 characters": {
"main": [
[
{
"node": "set git path",
"type": "main",
"index": 0
}
]
]
},
"get_selected_pattern_system_prompt": {
"main": [
[
{
"node": "set_system_prompt",
"type": "main",
"index": 0
}
]
]
},
"set_system_prompt": {
"main": [
[
{
"node": "Run chatInput with specialized tool",
"type": "main",
"index": 0
}
]
]
},
"Run chatInput with specialized tool": {
"main": [
[
{
"node": "set output",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Run chatInput with specialized tool",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "decide what pattern should be used",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Add User Message to DB": {
"main": [
[
{
"node": "cut first 100 characters",
"type": "main",
"index": 0
}
]
]
},
"Add AI Message to DB": {
"main": [
[
{
"node": "Prep Output Fields",
"type": "main",
"index": 0
}
]
]
},
"Prep Input Fields": {
"main": [
[
{
"node": "Add User Message to DB",
"type": "main",
"index": 0
}
]
]
},
"Prep Output Fields": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Webhook1": {
"main": [
[
{
"node": "Prep Input Fields",
"type": "main",
"index": 0
}
]
]
},
"set output": {
"main": [
[
{
"node": "Add AI Message to DB",
"type": "main",
"index": 0
}
]
]
},
"Clone fabric git": {
"main": [
[
{
"node": "get available prompts",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "bb23f0d1-7e70-4409-b1b5-a2933c1523a5",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "cdqdZBYXEvuSPsfp",
"tags": [
{
"createdAt": "2024-12-10T13:21:06.912Z",
"updatedAt": "2024-12-10T13:21:06.912Z",
"id": "0tXJXfH2daB7QdK5",
"name": "studio-test"
}
]
}
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.
httpHeaderAuthopenAiApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Smart Select Multi Tool Agent. Uses git, executeCommand, chainLlm, lmChatOpenAi. Webhook trigger; 21 nodes.
Source: https://github.com/DPabloFlores/ottomator-agents/blob/main/smart-select-multi-tool-agent/Smart_Select_Multi_Tool_Agent.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
Docsify example. Uses convertToFile, extractFromFile, html, sort. Webhook trigger; 60 nodes.
Read Write File, n8n, Chain Llm +4
This workflow creates a documentation system for n8n instances using Docsify.js. It serves a dynamic documentation website that allows users to: View an overview of all workflows in a tabular format F
Read Write File, n8n, Chain Llm +4
Content Creator. Uses lmChatOpenAi, httpRequest, supabase, outputParserStructured. Webhook trigger; 22 nodes.
OpenAI Chat, HTTP Request, Supabase +3
IA Professor de Espanhol de Tecnologia (Corrigido v2). Uses supabase, crypto, agent, lmChatOpenAi. Webhook trigger; 18 nodes.
Supabase, Crypto, Agent +4