Mindket

Email summaries from OpenRouter sent to a LINE chat

Newversion 1 · updated

Overview

An n8n workflow that reads new mail over IMAP, has a model on OpenRouter summarize each message and pushes the summary to a LINE chat.

Email summaries from OpenRouter sent to a LINE chat is an n8n workflow in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file there and activate it
  • Your own n8n server: the same file and steps
  • OpenRouter: the model that writes the summaries
  • LINE: the chat that receives them

Platform

Connects 3 apps

How it works

Trigger

New unread email

It starts when an unread email arrives in the IMAP inbox:

  • The mailbox login, in the IMAP credential
  • The OpenRouter key, in a Header Auth credential
  • The LINE channel access token and user id, in the last node

Actions

  1. The sender, subject and text of the email go to a model on OpenRouter
  2. The model writes a short summary, with deadlines and action items first when the email matters
  3. The summary is pushed to the LINE user as a text message

Result

A short summary of each new email, delivered to a LINE chat

Integrations

What you need before you start.

Email (IMAP and SMTP)

Mailbox

Supplies new unread mail over IMAP and leaves it unread.

NeedsAn IMAP host, port and login

OpenRouter

Language model

Summarizes each email with a Llama model.

NeedsAn OpenRouter API key in a Header Auth credential

LINE

Messenger

Receives the summary as a pushed text message.

NeedsA channel access token and a user id

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
It has no trigger node, so a run reaches no step
API keys
No API key is left in the file

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow reads new mail over IMAP and sends each message to a model on OpenRouter. The model writes a short summary, and deadlines and action items come first when the mail matters. The summary is pushed to a LINE chat through LINE’s Messaging API. Three nodes run it, beside four sticky notes.

Who it suits

People who live in LINE and want their inbox condensed into short messages there. Skip it if you have no LINE channel with the Messaging API, or if you cannot send mail text to OpenRouter and its model providers.

Who uses it, and how
IndustryWho uses itHow they use itExample
FamilyParentsCatch school and club deadlinesA parent gets the date a form is due in a chat message.
FreelanceFreelancersSkim client mail on the phoneA freelancer reads one line per message instead of opening the inbox.
OperationsSmall business ownersSpot payments and sign-up datesAn owner sees which supplier mail has a due date.
TravelFrequent travellersKeep booking mail shortA traveller gets one line per booking change.

You need a little n8n, a LINE channel and two API credentials: import a file, add three credentials and paste your LINE user id.

Where to use it

Any n8n that can reach your mail server, OpenRouter and LINE will run it. The summaries arrive in the LINE chat of the user id you set.

  • n8n Cloud: import the file there and activate it
  • Your own n8n server: the same file and steps
  • OpenRouter: the model that writes the summaries
  • LINE: the chat that receives them

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Setup takes three credentials and one user id.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
MailboxIMAP host, port and login
OpenRouterAn account and an API key
LINEA channel with the Messaging API, its channel access token and a user id
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add an Email (IMAP) credential and select it in Read emails (IMAP).
  3. Add a Header Auth credential with the name Authorization and the value Bearer <YOUR_OPENROUTER_API_KEY>, using your key, and select it in Send email to A.I. to summarize.
  4. Add a second Header Auth credential with the value Bearer <YOUR_LINE_CHANNEL_ACCESS_TOKEN> and select it in Send summarized content to messenger.
  5. In that node, replace <YOUR_LINE_USER_ID> with the receiver’s id.
  6. Activate the workflow and send yourself a mail.

How to use it

Activate the workflow and leave it running. A new unread mail is summarized, and the summary arrives in LINE a moment later. Edit the prompt to change what the summary stresses.

What to change for a different result
To changeWhere
The instructions to the modelThe prompt in Send email to A.I. to summarize
The modelmodel in the same body
Which mail is readThe mailbox and options of Read emails (IMAP)
Who receives the summaryto in the LINE body

Example

A parent gets a school email about a trip and a payment due on the first of the month.

The model replies with the due date in bold at the top and one line about the trip. LINE shows that message in the parent’s chat.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. Here one box reads the mail, one asks the model and one posts to LINE. Try it with a mailbox that gets little mail.

For experts. One IMAP trigger and two HTTP Request nodes with Header Auth, and no AI node. The email text is JSON-escaped inside the request body, and the summary is escaped the same way before the push.

Where to look closer
NodeWhat it doesWhat to know
Read emails (IMAP)Fires for unread mail and leaves it unreadVersion 2.2 remembers the last message id
Send email to A.I. to summarizePosts the mail to OpenRouter’s chat completions addressThe model id is in the body
Send summarized content to messengerPushes the text to LINEThe receiver is the to user id

Good to know

Every unread mail becomes a model call and a LINE push, so a busy inbox can add up in cost.

  • The repair: OpenRouter’s public model list, read on 12 November 2026, no longer shows meta-llama/llama-3.1-70b-instruct:free. The same model without :free is listed, so this copy uses it, and it is no longer free
  • The IMAP node: version 2 fetches every unread message again on each arrival when mail is left unread, so this copy uses version 2.2
  • The prompt: the mail text was URL-encoded before. It is JSON-escaped now, and the plain text part is used first
  • LINE: its pricing page, read on 12 November 2026, counts push messages toward the plan’s message count
  • Not run: this copy was not run against a mail server, OpenRouter or LINE
  • Your data: the sender, subject and text go to OpenRouter and its model provider, and the summary goes to LINE
  • Credentials: the JSON holds none

README and files

README

Email summaries from OpenRouter sent to a LINE chat

An n8n workflow that reads new mail over IMAP, sends each message to a model on OpenRouter for a short summary, and pushes the summary to a LINE chat through LINE's Messaging API.

What is inside

  • workflow.json: the workflow as n8n exports it, seven nodes: three that do the work and four sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The credential links are gone. Select your own for IMAP and for the two Header Auth steps.
  • The model was meta-llama/llama-3.1-70b-instruct:free. OpenRouter's public model list, read on 12 November 2026, no longer shows it. The same model without :free is listed with a context of 131072 tokens and a price of 0.00000072 USD per token for input and output, and the node uses it. It is no longer free.
  • Read emails (IMAP) moves from version 2 to 2.2. In n8n's source, versions up to 2 do not remember the last message seen, and this file leaves mail unread after processing. Each new arrival would then fetch every unread message again. Version 2.2 follows the message ids.
  • The email text in the prompt was URL-encoded, which keeps quotes and line breaks from breaking the JSON body but gives the model percent-encoded text. It is JSON-escaped now, and the plain text part is used, with the HTML part as a fallback. The summary sent to LINE is escaped the same way, so a quote in it cannot break the request.
  • The LINE user id is <YOUR_LINE_USER_ID> now.
  • The notes are rewritten. Two links and a remark about LINE's own node are removed.
  • Nothing else.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • A mailbox you can reach over IMAP, with its host, port and login.
  • An OpenRouter account and an API key.
  • A LINE channel with the Messaging API, its channel access token, and the user id of the person who should get the summaries.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add an Email (IMAP) credential and select it in Read emails (IMAP).
  3. Add a Header Auth credential for OpenRouter. Set the name to Authorization and the value to Bearer <YOUR_OPENROUTER_API_KEY>, with your key in place of the placeholder. Select it in Send email to A.I. to summarize.
  4. Add a second Header Auth credential for LINE with the name Authorization and the value Bearer <YOUR_LINE_CHANNEL_ACCESS_TOKEN>. Select it in Send summarized content to messenger.
  5. In that node, replace <YOUR_LINE_USER_ID> with the receiver's user id.
  6. Save and activate the workflow, then send yourself a mail.

How a run goes

  1. Read emails (IMAP) reads the inbox and fires for unread mail. It leaves each message unread.
  2. Send email to A.I. to summarize posts the sender, subject and text to OpenRouter's chat completions address. The prompt asks for a summary of under ten words when the mail is unimportant, and for deadlines and action items, with an urgent marker, when it matters.
  3. Send summarized content to messenger posts the summary as a text message to LINE's push address.

Change the look

  • The instructions to the model: the prompt in Send email to A.I. to summarize.
  • The model: model in the same body.
  • Which mail is read: the mailbox and options in Read emails (IMAP).
  • Who receives the summary: to in the LINE body.

Good to know

  • LINE's pricing page, read on 12 November 2026, counts push messages toward a plan's message count. Reply messages are not counted.
  • OpenRouter bills the model per token.
  • An email with only an HTML part sends that HTML to the model, which makes a long prompt.
  • This copy was not run against a mail server, OpenRouter or LINE.
  • The sender, subject and body go to OpenRouter and its model provider. The summary goes to LINE.
  • The JSON holds no credential.
Files
NOTICE.md  679 B
README.md  4 KB
workflow.json  5 KB

3 files, 10 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New

Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…

New

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Similar in Productivity

See all in Productivity

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Frontend Slides

zarazhangrui · Skill

Builds HTML presentations from scratch or from a PowerPoint file and shows visual style previews to pick from, for people who want web slides with no CSS or Ja…

New32.3k

IPTV

iptv-org · Kit

Collects publicly available live TV channels from many countries into playlists that any video player with live streaming can open. Made for viewers and for de…

New144k