This workflow follows the Agent → Gmail 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "43e68fe1-7f48-4bc9-b19a-66d39bee5bbd",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-520,
20
],
"parameters": {},
"typeVersion": 1
},
{
"id": "32aa401a-60c3-4436-94d5-5ba09d3be6ae",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
80,
0
],
"parameters": {
"model": "openai/gpt-4.1-nano",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "f6d325b4-ff87-4bba-9f27-b68590c8a533",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-520,
-220
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "8e10c622-9bf8-414b-8364-185c5c4808a0",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-600,
-480
],
"parameters": {
"width": 1660,
"height": 680,
"content": "## Mail Agent\nFor emails in the inbox, archive those that are completely unnecessary, and label the rest based on their relevance.\n\n"
},
"typeVersion": 1
},
{
"id": "2e664cd4-37af-4b8f-84a5-ff07911b8aaa",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-560,
-380
],
"parameters": {
"color": 5,
"width": 180,
"height": 360,
"content": "### Trigger\nRun by communicating with Telegram"
},
"typeVersion": 1
},
{
"id": "966af8d0-bfca-40fa-b97c-ec1bb7de82d2",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
-380
],
"parameters": {
"color": 4,
"width": 180,
"height": 360,
"content": "### Get Mail via Gmail\nRetrieve all emails in the Gmail inbox.\n(Inbox = Label: INBOX)"
},
"typeVersion": 1
},
{
"id": "07dabeda-a075-4e45-9ecf-9a0e6d0df0b2",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-160,
-380
],
"parameters": {
"color": 4,
"width": 180,
"height": 360,
"content": "### Filter\nFilter out emails that have already been processed to avoid unnecessary work for the AI.\n\n"
},
"typeVersion": 1
},
{
"id": "b9a96646-283e-4328-8c79-57befa97bb69",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
40,
-380
],
"parameters": {
"color": 3,
"width": 980,
"height": 540,
"content": "### AI Agent\nCheck each email one by one, categorize them as necessary or unnecessary according to the provided prompt, and instruct Gmail to apply the appropriate labels."
},
"typeVersion": 1
},
{
"id": "32c73c57-61b5-430b-a011-f0b44fa2b226",
"name": "mail_label_setter",
"type": "n8n-nodes-base.gmailTool",
"position": [
360,
0
],
"parameters": {
"labelIds": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Label_Names_or_IDs', ``, 'string') }}",
"messageId": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message_ID', ``, 'string') }}",
"operation": "addLabels"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "7cf38850-939c-4c8e-af62-1f730d5b7e34",
"name": "mail_archiver",
"type": "n8n-nodes-base.gmailTool",
"position": [
220,
0
],
"parameters": {
"labelIds": [
"INBOX"
],
"messageId": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message_ID', ``, 'string') }}",
"operation": "removeLabels"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "5fab497e-a632-4565-8048-7ae9b209728d",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"position": [
380,
-220
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "f7144884-6ba6-4e97-be35-f5f8b27d56ad",
"name": "Telegram",
"type": "n8n-nodes-base.telegram",
"position": [
820,
-220
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "9236fbc1-ffad-4bf0-b3a1-5d389e5b422c",
"name": "OpenRouter Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
520,
0
],
"parameters": {
"model": "openai/gpt-4.1-nano",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "e0ec10ca-ad72-4784-891e-5bd5bcff7082",
"name": "Reporter",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
520,
-220
],
"parameters": {
"text": "=Summarize data\n```\n{{ $json.data.map(item => item.output + '\\n\\n') }}\n```\n",
"options": {
"systemMessage": "=# persona\n* You are a helpful assistant.\n"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "9b4f8e14-7b9c-45b3-97cb-32f2fe756440",
"name": "Get mails in INBOX",
"type": "n8n-nodes-base.gmail",
"position": [
-320,
-220
],
"parameters": {
"filters": {
"labelIds": [
"INBOX"
]
},
"operation": "getAll",
"returnAll": true
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "13088de9-6f96-463e-bcb6-92f97d7144d9",
"name": "Filter processed",
"type": "n8n-nodes-base.filter",
"position": [
-120,
-220
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "1091eba0-3d75-47b6-92c5-404f93e263ae",
"operator": {
"type": "array",
"operation": "notContains",
"rightType": "any"
},
"leftValue": "={{ $json.labels.map(item => item.name)}}",
"rightValue": "NotNeed"
},
{
"id": "31160689-98ce-43ac-8c7b-116cd7da5ebc",
"operator": {
"type": "array",
"operation": "notContains",
"rightType": "any"
},
"leftValue": "={{ $json.labels.map(item => item.name)}}",
"rightValue": "MustRead"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "317ea413-e8fd-4148-8115-8b4d2b9a7fe4",
"name": "Categoriser",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
80,
-220
],
"parameters": {
"text": "=<task>\nProcess mail\n</task>\n<mail>\n<id>{{ $json.id }}</id>\n<from>{{ $json.From }}</from>\n<subject>{{ $json.Subject }}</subject>\n<body>{{ $json.snippet }}</body>\n</mail>",
"options": {
"systemMessage": "=<persona>\nYou are an email processing assistant.\n</persona>\n<task>\nLook at the content of the email and decide whether to apply a label or archive it, processing it only once. First, archive those that are absolutely unnecessary using the mail_archiver tool. This judgment is the top priority. After that, if it does not fall into that category, determine whether it should be read based on the following criteria and use the mail_label_setter tool to apply the label.\n<case>Absolutely unnecessary: Archive using the mail_archiver tool</case>\n<case>Needs to be read: Apply \"Label_[label_id]\" using the mail_label_setter tool</case>\n<case>Other: Apply \"Label_[label_id]\" using the mail_label_setter tool</case>\nReport the processing results carefully.\n</task>\n<rules>\n<Archive>\nEmails that are absolutely unnecessary and will be archived\n<item>[list up your rule1]</item>\n<item>[list up your rule2]</item>\n</Archive><MustRead>\nEmails that need to be read\n<item>[list up your rule1]</item>\n<item>[list up your rule2]</item>\n</MustRead>\n<Other>\nEmails that are not necessary to read but will not be archived\n<item>[list up your rule1]</item>\n<item>[list up your rule2]</item>\n</Other>\n</rules>"
},
"promptType": "define"
},
"typeVersion": 1.7
}
],
"connections": {
"Reporter": {
"main": [
[
{
"node": "Telegram",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Reporter",
"type": "main",
"index": 0
}
]
]
},
"Categoriser": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"mail_archiver": {
"ai_tool": [
[
{
"node": "Categoriser",
"type": "ai_tool",
"index": 0
}
]
]
},
"Filter processed": {
"main": [
[
{
"node": "Categoriser",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Get mails in INBOX",
"type": "main",
"index": 0
}
]
]
},
"mail_label_setter": {
"ai_tool": [
[
{
"node": "Categoriser",
"type": "ai_tool",
"index": 0
}
]
]
},
"Get mails in INBOX": {
"main": [
[
{
"node": "Filter processed",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "Categoriser",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenRouter Chat Model1": {
"ai_languageModel": [
[
{
"node": "Reporter",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Get mails in INBOX",
"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.
gmailOAuth2openRouterApitelegramApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow empowers Telegram users to effortlessly export and organise filtered messages from their chats, saving hours of manual sorting and ensuring important conversations are preserved without clutter. It is ideal for individuals or teams managing high-volume Telegram groups, such as project coordinators or community managers, who need to archive specific discussions for compliance or reference. The key step involves an AI-powered filter using OpenRouter's chat model to intelligently categorise incoming messages from the Telegram trigger, seamlessly forwarding relevant ones to Gmail for secure storage and easy searchability.
Use this workflow when you receive frequent Telegram updates and want automated, context-aware exports to avoid missing critical information amid noise. Avoid it for low-volume personal chats where manual handling suffices, or if you lack API access to Telegram and Gmail. Common variations include tweaking the AI prompts for custom filters, like sentiment analysis, or integrating additional tools for direct exports to cloud storage instead of email.
About this workflow
Telegram Filter Export. Uses manualTrigger, lmChatOpenRouter, telegramTrigger, stickyNote. 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.
This workflow is perfect for busy professionals, students, or anyone who struggles to keep their Gmail inbox organized and clutter-free.
Arvifund - Supabase (Fixed v6). Uses httpRequest, telegram, supabase, telegramTrigger. Event-driven trigger; 92 nodes.
Arvifund - Supabase (Fixed v5). Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 91 nodes.
Arvifund - Supabase. Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 90 nodes.
Arvifund - Supabase (Fixed v2). Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 90 nodes.