This workflow follows the Agent → Execute Workflow Trigger 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": "02 - AI Agent Chat",
"nodes": [
{
"id": "n0",
"name": "Trigger",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1,
"position": [
100,
300
],
"parameters": {}
},
{
"id": "n1",
"name": "Get Brain Context",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
320,
300
],
"parameters": {
"method": "GET",
"url": "=http://host.docker.internal:4242/brain/context",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "chat_id",
"value": "={{ $json.chatId }}"
},
{
"name": "message",
"value": "={{ encodeURIComponent($json.message) }}"
}
]
},
"options": {
"response": {
"response": {
"neverError": true
}
},
"timeout": 10000
}
}
},
{
"id": "n2",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.7,
"position": [
560,
300
],
"parameters": {
"promptType": "define",
"text": "={{ $('Trigger').item.json.message }}",
"systemMessage": "={{ $('Get Brain Context').item.json.system_prompt }}\n\nCurrent time: {{ $now.toISO() }}\nOwner chat_id: {{ $('Trigger').item.json.chatId }}",
"options": {
"maxIterations": 8,
"returnIntermediateSteps": false,
"passthroughBinaryImages": false
}
}
},
{
"id": "n2-memory",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
560,
480
],
"parameters": {
"sessionKey": "={{ $('Trigger').item.json.chatId }}",
"contextWindowLength": 20
}
},
{
"id": "n2-model",
"name": "Gemini Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
400,
480
],
"parameters": {
"modelName": "gemini-2.0-flash-001",
"options": {
"maxOutputTokens": 2048,
"temperature": 0.7
}
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"id": "tool-execute",
"name": "Mac Agent Execute",
"type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
"typeVersion": 1.1,
"position": [
730,
480
],
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:4242/execute",
"name": "execute",
"description": "Execute actions on the owner's Mac. Tools: shell (run commands), file_read, file_write, notify (macOS notification), open_url, brain_note (remember a fact), brain_recall (search memory), brain_stats, brain_new_session.\nPass: {\"tool\": \"<tool_name>\", \"args\": {\"chat_id\": \"<chatId>\", ...tool_args}}",
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "tool",
"value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('tool', 'The tool name to execute', 'string') }}"
},
{
"name": "args",
"value": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('args', 'Tool arguments as JSON object', 'json') }}"
}
]
},
"options": {
"response": {
"response": {
"neverError": true
}
},
"timeout": 35000
},
"placeholderDefinitions": {
"values": [
{
"name": "tool",
"description": "Tool name: shell, file_read, file_write, notify, open_url, brain_note, brain_recall, brain_stats, brain_new_session",
"type": "string"
},
{
"name": "args",
"description": "Tool arguments object. Always include chat_id for brain tools. For shell: {\"command\": \"...\"}. For brain_note: {\"fact\": \"...\", \"category\": \"...\", \"chat_id\": \"...\"}. For brain_recall: {\"query\": \"...\", \"chat_id\": \"...\"}.",
"type": "json"
}
]
}
}
},
{
"id": "n3",
"name": "Send Reply",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
800,
300
],
"parameters": {
"chatId": "={{ $('Trigger').item.json.chatId }}",
"text": "={{ $json.output }}",
"additionalFields": {
"parse_mode": "Markdown"
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"continueOnFail": true
},
{
"id": "n4",
"name": "Save to Brain",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1020,
300
],
"parameters": {
"method": "GET",
"url": "http://host.docker.internal:4242/brain/save-get",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "chat_id",
"value": "={{ $('Trigger').item.json.chatId }}"
},
{
"name": "role",
"value": "user"
},
{
"name": "content",
"value": "={{ encodeURIComponent($('Trigger').item.json.message) }}"
},
{
"name": "provider",
"value": "gemini-agent"
}
]
},
"options": {
"response": {
"response": {
"neverError": true
}
},
"timeout": 5000
}
},
"continueOnFail": true
},
{
"id": "n4b",
"name": "Save AI Reply",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1020,
420
],
"parameters": {
"method": "GET",
"url": "http://host.docker.internal:4242/brain/save-get",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "chat_id",
"value": "={{ $('Trigger').item.json.chatId }}"
},
{
"name": "role",
"value": "assistant"
},
{
"name": "content",
"value": "={{ encodeURIComponent($('AI Agent').item.json.output) }}"
},
{
"name": "provider",
"value": "gemini-agent"
}
]
},
"options": {
"response": {
"response": {
"neverError": true
}
},
"timeout": 5000
}
},
"continueOnFail": true
},
{
"id": "n5",
"name": "Extract Facts",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1240,
300
],
"parameters": {
"method": "GET",
"url": "http://host.docker.internal:4242/brain/extract",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "chat_id",
"value": "={{ $('Trigger').item.json.chatId }}"
},
{
"name": "user_text",
"value": "={{ encodeURIComponent($('Trigger').item.json.message) }}"
},
{
"name": "ai_text",
"value": "={{ encodeURIComponent($('AI Agent').item.json.output) }}"
}
]
},
"options": {
"response": {
"response": {
"neverError": true
}
},
"timeout": 20000
}
},
"continueOnFail": true
},
{
"id": "n-error",
"name": "Error Handler",
"type": "n8n-nodes-base.telegram",
"typeVersion": 1.2,
"position": [
800,
500
],
"parameters": {
"chatId": "={{ $('Trigger').item.json.chatId }}",
"text": "Hmm, couldn't reach my brain right now. Try again in a moment? \ud83d\ude43",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Trigger": {
"main": [
[
{
"node": "Get Brain Context",
"type": "main",
"index": 0
}
]
]
},
"Get Brain Context": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Send Reply",
"type": "main",
"index": 0
}
]
],
"error": [
[
{
"node": "Error Handler",
"type": "main",
"index": 0
}
]
]
},
"Send Reply": {
"main": [
[
{
"node": "Save to Brain",
"type": "main",
"index": 0
},
{
"node": "Save AI Reply",
"type": "main",
"index": 0
}
]
]
},
"Save to Brain": {
"main": [
[
{
"node": "Extract Facts",
"type": "main",
"index": 0
}
]
]
},
"Windows Buffer Memory": {},
"Gemini Model": {},
"Mac Agent Execute": {}
},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true,
"callerPolicy": "workflowsFromSameOwner",
"errorWorkflow": ""
},
"meta": {
"description": "Agentic AI chat via n8n AI Agent node (Gemini 2.0 Flash). Reply-first ordering: user gets response before save/extract. Fallback error handler sends friendly message if AI Agent fails."
}
}
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.
googlePalmApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
02 - AI Agent Chat. Uses executeWorkflowTrigger, httpRequest, agent, memoryBufferWindow. Event-driven trigger; 11 nodes.
Source: https://github.com/rohankag/ronkbot/blob/db03432335532bdeb4ebcee0c72d9109e04b466f/n8n-workflows/02-gemini-chat.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.
This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents.
Tool Http Request, Agent, HTTP Request +27
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Output Parser Structured, Telegram, N8N Nodes Tesseractjs +14
Automated Research Report Generation with OpenAI, Wikipedia, Google Search, and Gmail/Telegram. Uses lmChatOpenAi, memoryBufferWindow, toolHttpRequest, agent. Event-driven trigger; 26 nodes.
OpenAI Chat, Memory Buffer Window, Tool Http Request +8
This workflow automates the process of generating professional research reports for researchers, students, and professionals. It eliminates manual research and report formatting by aggregating data, g
OpenAI Chat, Memory Buffer Window, Tool Http Request +8
This is a fully automated, end-to-end pipeline designed to solve the challenge of inconsistent and low-quality lead data from large-scale scraping operations. The system programmatically fetches raw l
Execute Workflow Trigger, Agent, Google Gemini Chat +4