This workflow follows the Agent → Ollama 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 →
{
"id": "QyMyf3zraY0wxXDf",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Load Prompts from Github Repo and auto populate n8n expressions",
"tags": [],
"nodes": [
{
"id": "34781446-b06e-41eb-83b8-b96bda1a5595",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-80,
0
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c53b7243-7c82-47e0-a5ee-bd82bc51c386",
"name": "GitHub",
"type": "n8n-nodes-base.github",
"position": [
600,
0
],
"parameters": {
"owner": {
"__rl": true,
"mode": "name",
"value": "={{ $json.Account }}"
},
"filePath": "={{ $json.path }}{{ $json.prompt }}",
"resource": "file",
"operation": "get",
"repository": {
"__rl": true,
"mode": "name",
"value": "={{ $json.repo }}"
},
"additionalParameters": {}
},
"credentials": {
"githubApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "9976b199-b744-47a7-9d75-4b831274c01b",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
840,
0
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1
},
{
"id": "26aa4e6a-c487-4cdf-91d5-df660cf826a6",
"name": "setVars",
"type": "n8n-nodes-base.set",
"position": [
180,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "150618c5-09b1-4f8b-a7b4-984662bf3381",
"name": "Account",
"type": "string",
"value": "TPGLLC-US"
},
{
"id": "22e8a3b0-bd53-485c-b971-7f1dd0686f0e",
"name": "repo",
"type": "string",
"value": "PeresPrompts"
},
{
"id": "ab94d0a1-ef3a-4fe9-9076-6882c6fda0ac",
"name": "path",
"type": "string",
"value": "SEO/"
},
{
"id": "66f122eb-1cbd-4769-aac8-3f05cdb6c116",
"name": "prompt",
"type": "string",
"value": "keyword_research.md"
},
{
"id": "03fe26a3-04e6-439c-abcb-d438fc5203c0",
"name": "company",
"type": "string",
"value": "South Nassau Physical Therapy"
},
{
"id": "c133d216-a457-4872-a060-0ba4d94549af",
"name": "product",
"type": "string",
"value": "Manual Therapy"
},
{
"id": "584864dd-2518-45e2-b501-02828757fc3a",
"name": "features",
"type": "string",
"value": "pain relief"
},
{
"id": "0c4594cc-302a-4215-bdad-12cf54f57967",
"name": "sector",
"type": "string",
"value": "physical therapy"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "9d92f581-8cd9-448c-aa1d-023a96c1ddda",
"name": "replace variables",
"type": "n8n-nodes-base.code",
"position": [
1900,
-20
],
"parameters": {
"jsCode": "// Fetch the prompt text\nconst prompt = $('SetPrompt').first().json.data; // Ensure the prompt contains placeholders like {{ some.node.value }}\n\n// Example variables object\nconst variables = {\n company: $('setVars').first().json.company,\n features: \"Awesome Software\",\n keyword: \"2025-02-07\"\n};\n\n// Function to replace placeholders dynamically\nconst replaceVariables = (text, vars) => {\n return text.replace(/{{(.*?)}}/g, (match, key) => {\n const trimmedKey = key.trim();\n \n // Extract last part after the last dot\n const finalKey = trimmedKey.split('.').pop();\n\n // Replace if key exists, otherwise leave placeholder unchanged\n return vars.hasOwnProperty(finalKey) ? vars[finalKey] : match;\n });\n};\n\n// Replace and return result\nreturn [{\n prompt: replaceVariables(prompt, variables)\n}];\n"
},
"typeVersion": 2
},
{
"id": "6c6c4fde-6ee5-47a8-894d-44d1afcedc2a",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
1560,
0
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2717a7e5-095a-42bf-8b5b-8050c3389ec5",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.success }}",
"rightValue": "={{ $('Check All Prompt Vars Present').item.json.keys()}}"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "3b7712b8-5152-4f60-9401-03c89c39e227",
"name": "Check All Prompt Vars Present",
"type": "n8n-nodes-base.code",
"position": [
1280,
0
],
"parameters": {
"jsCode": "// Get prompt text\nconst prompt = $json.data;\n\n// Extract variables inside {{ }} dynamically\nconst matches = [...prompt.matchAll(/{{(.*?)}}/g)];\nconst uniqueVars = [...new Set(matches.map(match => match[1].trim().split('.').pop()))];\n\n// Get variables from the Set Node\nconst setNodeVariables = $node[\"setVars\"].json || {};\n\n// Log extracted variables and Set Node keys\nconsole.log(\"Extracted Variables:\", uniqueVars);\nconsole.log(\"Set Node Keys:\", Object.keys(setNodeVariables));\n\n// Check if all required variables are present in the Set Node\nconst missingKeys = uniqueVars.filter(varName => !setNodeVariables.hasOwnProperty(varName));\n\nconsole.log(\"Missing Keys:\", missingKeys);\n\n// Return false if any required variable is missing, otherwise return true\nreturn [{\n success: missingKeys.length === 0,\n missingKeys: missingKeys\n}];\n"
},
"typeVersion": 2
},
{
"id": "32618e10-3285-4c16-9e78-058dde329337",
"name": "SetPrompt",
"type": "n8n-nodes-base.set",
"position": [
1060,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "335b450d-542a-4714-83d8-ccc237188fc5",
"name": "data",
"type": "string",
"value": "={{ $json.data }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "4d8b34ca-50dd-4f37-b4f7-542291461662",
"name": "Stop and Error",
"type": "n8n-nodes-base.stopAndError",
"position": [
1900,
200
],
"parameters": {
"errorMessage": "=Missing Prompt Variables : {{ $('Check All Prompt Vars Present').item.json.missingKeys }}\n"
},
"typeVersion": 1
},
{
"id": "a78c1e17-9152-4241-bcdf-c0d723da543b",
"name": "Set Completed Prompt",
"type": "n8n-nodes-base.set",
"position": [
2220,
-20
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "57a9625b-adea-4ee7-a72a-2be8db15f3d4",
"name": "Prompt",
"type": "string",
"value": "={{ $json.prompt }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "51447c90-a222-4172-a49b-86ec43332559",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2440,
-20
],
"parameters": {
"text": "={{ $json.Prompt }}",
"options": {},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "f15b6af1-7af2-4515-be8f-960211118dce",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
60,
-120
],
"parameters": {
"width": 340,
"height": 260,
"content": "# Set The variables in your prompt here"
},
"typeVersion": 1
},
{
"id": "163db6cc-5b06-4ae6-ac97-5890b37cdb18",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
520,
-120
],
"parameters": {
"color": 5,
"content": "## The repo is currently public for you to test with"
},
"typeVersion": 1
},
{
"id": "83ff6a86-a759-42a9-ace4-e20d57b906db",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1780,
-200
],
"parameters": {
"width": 360,
"height": 260,
"content": "## Replaces the values in the prompt with the variables in the \n# 'setVars' Node"
},
"typeVersion": 1
},
{
"id": "7dd61153-84ac-4b59-b449-333825476c33",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
2000,
180
],
"parameters": {
"color": 3,
"content": "## If you're missing variables they will be listed here"
},
"typeVersion": 1
},
{
"id": "1f070dc3-3d25-41d8-b534-912ba7c8b2b0",
"name": "Prompt Output",
"type": "n8n-nodes-base.set",
"position": [
2800,
-20
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "01a30683-c348-4712-a3b1-739fc4a17718",
"name": "promptResponse",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "2d12a6e2-7976-41b0-8cb2-01466b28269d",
"name": "Ollama Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"position": [
2480,
200
],
"parameters": {
"options": {}
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "4327a337-59e7-4b5b-98e8-93c6be550972",
"connections": {
"If": {
"main": [
[
{
"node": "replace variables",
"type": "main",
"index": 0
}
],
[
{
"node": "Stop and Error",
"type": "main",
"index": 0
}
]
]
},
"GitHub": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"setVars": {
"main": [
[
{
"node": "GitHub",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Prompt Output",
"type": "main",
"index": 0
}
]
]
},
"SetPrompt": {
"main": [
[
{
"node": "Check All Prompt Vars Present",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "SetPrompt",
"type": "main",
"index": 0
}
]
]
},
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"replace variables": {
"main": [
[
{
"node": "Set Completed Prompt",
"type": "main",
"index": 0
}
]
]
},
"Set Completed Prompt": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Check All Prompt Vars Present": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "setVars",
"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.
githubApiollamaApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow streamlines prompt management for n8n users by fetching custom AI prompts from a GitHub repository and automatically populating them into workflow expressions, saving hours of manual copying and pasting. It is ideal for developers and automation enthusiasts who maintain prompt libraries in version-controlled repos, ensuring consistency across projects without risking errors from outdated or mismatched variables. The key step involves extracting prompt content from the GitHub file using the extractFromFile node, followed by variable replacement and validation to integrate seamlessly with AI tools like Ollama's lmChat.
Use this workflow when building event-driven automations that rely on dynamic, repo-sourced prompts for tasks such as content generation or data analysis, particularly if your team collaborates on prompt refinements via GitHub. Avoid it for one-off tests or static prompts that do not benefit from version control, as the setup overhead may not justify the automation. Common variations include adapting the GitHub node to pull from private repos with authentication or extending the chain to deploy prompts directly into multiple n8n workflows.
About this workflow
Load Prompts from Github Repo and auto populate n8n expressions. Uses manualTrigger, github, extractFromFile, stopAndError. Event-driven trigger; 17 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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.
Load Prompts from Github Repo and auto populate n8n expressions. Uses manualTrigger, github, extractFromFile, stopAndError. Event-driven trigger; 17 nodes.
This workflow is designed for AI engineers, automation specialists, and content creators who need a scalable system to dynamically manage prompts stored in GitHub. It eliminates manual updates, enforc
This n8n template demonstrates how to automatically process PDF purchase orders received via email and convert them into sales orders in Adobe Commerce (Magento 2) using Company Credit as the payment
Episode 11: AI shorts factory app. Uses httpRequest, googleSheets, lmChatOpenAi, lmChatOllama. Event-driven trigger; 96 nodes.
How it Works