The Ultimate n8n TemplatesLibrary & Marketplace

Discover 7000+ premium n8n templates with AI-powered generation. The largest n8n templates marketplace enabling anyone to have a running workflow in 5 minutes

Start AI Generation Browse Templates

Or browse our extensive n8n templates collection. Try the AI generator to create custom n8n templates instantly.

13904+

Templates

50+

Integrations

50k+

Downloads

Latest n8n Templates

Freshly updated automation workflows to keep your n8n stack current

View All

Fill any PDF from JSON data with JustFill and Google Gemini vision

Quick overview This workflow collects a PDF and a JSON payload via an n8n form, uses JustFill to detect fields and render previews, then uses Google Gemini Vision to map data to field IDs and visually review the filled result before generating a downloadable filled PDF. How it works Receives a PDF upload and a “Data JSON” object through an n8n form. Requests an upload slot from JustFill, uploads the PDF, and opens it to detect fillable fields and create a workspace. Renders labelled page previews for all pages with detected fields using JustFill. Sends the labelled previews plus the user’s JSON keys to Google Gemini to map each data key to a specific JustFill field ID. Renders filled previews with the proposed values and asks Google Gemini to independently review the placement and readability across pages. If Gemini approves with no issues, fills the PDF in JustFill and returns a redirect link to download the completed document. Setup Add a JustFill API key and a Google Gemini API key, then paste them into the Config step (including the model name, if you want to change it). Ensure your JustFill account can access the MCP tools used by the workflow (request_file_upload, open_pdf, render_preview, render_filled_preview, and fill_pdf). Customize the n8n form fields (and any sample JSON) to match the kinds of data you plan to submit, then copy the form URL for users who will upload PDFs. Requirements A JustFill API key. The free plan works for testing, downloads are watermarked. You also need a Google Gemini API key for the vision model set in Config. Customization Swap the n8n form for a webhook, a Google Sheets row or your CRM, and change the model name in Config if you prefer another Gemini model. For a form you fill often, save it as a JustFill template and use the simpler template-based workflow instead.

BeginnerManual Trigger

by jusftfill.app

Reply to WhatsApp leads with Google Gemini and Cal.com booking

Quick overview This workflow listens for incoming WhatsApp messages and uses Google Gemini plus optional TinyFish web research to draft concise replies, including offering and booking Cal.com meeting slots when requested, then sends the response back to the same WhatsApp contact. How it works Triggers when a new WhatsApp message is received. Checks that the incoming message contains text and ignores non-text messages. Adds booking and context fields (Cal.com link, event type, timezone, sender details, and message text) to the incoming payload. Uses a Google Gemini-powered agent with short-term chat memory to draft a reply, optionally calling TinyFish Search/Web Agent for lead research and Cal.com Slots/Book to propose and confirm meeting times. Sanitizes the generated response to ensure it is never empty and stays within a safe length limit. Sends the final reply back to the original sender via WhatsApp. Setup Connect WhatsApp Cloud API credentials for both the WhatsApp Trigger and WhatsApp send action, and ensure your WhatsApp app is configured to deliver message webhooks to n8n. Add a Google Gemini (PaLM) API credential for the chat model used by the agent. Add a Cal.com API key credential and set your Cal.com booking URL, eventTypeId, timezone, and lookahead days in the Booking Config step. (Optional) Add TinyFish credentials if you want the agent to perform web research about people or companies mentioned in chats.

BeginnerManual Trigger

Track weekend flight prices with Google Flights, SerpAPI, OpenAI and Telegram

Quick overview This workflow lets you create, list, cancel, and check weekend flight price alerts via Telegram (text or voice) and runs a daily schedule to price active routes using Google Flights results from SerpAPI, storing alert state in n8n Data Tables and sending deal digests back to Telegram. How it works Triggers either when a Telegram message/voice note is received or every day at 08:00 (server timezone). For Telegram voice messages, downloads the audio from Telegram and transcribes it with OpenAI, then normalizes all inputs into a single request format. Uses OpenAI to parse the user’s intent (create/list/cancel/status) and route preferences (airports, budget, window, weekend pattern, cadence) and converts them into concrete search dates and airport lists. For new alerts, fetches a sample Google Flights result via SerpAPI to validate the budget, generates an alert card, saves the alert to an n8n Data Table, and confirms creation in Telegram. For list/cancel/status requests, reads the alerts or run log from n8n Data Tables, applies the requested action (including marking an alert cancelled), and replies in Telegram. On scheduled runs, loads active alerts from the Data Table, queries Google Flights via SerpAPI for the relevant weekend date pairs, aggregates the cheapest option per weekend, and formats a ranked digest with booking links. Sends the digest to Telegram when results meet the notification rules, then logs the run and updates each alert’s last checked and last seen price in the Data Table. Setup Create a Telegram bot with @BotFather, add a Telegram credential in n8n, and enable the Telegram Trigger so it can receive updates. Add an OpenAI credential for both intent parsing and voice transcription. Add a SerpAPI credential with Google Flights access and ensure your plan/quota can cover the number of searches your alerts generate. Create two n8n Data Tables (for alerts and for the run log) with the required columns, then select their table IDs in all Data Table nodes used by the workflow. Update the Config values (home airport, max searches per run, and the admin_chat_id for error notifications) before activating the workflow.

Review content drafts for repetition, substance, tone and style using code

Quick overview Before you publish, this compares each draft in your content calendar against your last 30 published posts and flags the ones that will read as more of the same, then writes the reason back into the sheet. How it works Runs every morning at 09:00 on a schedule trigger, or on demand with the manual trigger. Reads rows marked ready from a Drafts tab in Google Sheets, and your last 30 posts from a Published tab. Compares wording with bigram overlap (Jaccard). Word bigrams for languages with spaces, character bigrams for Chinese, Japanese and Thai, chosen automatically. Compares structure on four signals: opening pattern, ending type, line and paragraph rhythm, and filler-phrase set. These are what make posts feel identical even when the words differ. Flags a draft only when both trip: wording overlap above the threshold AND at least two structural signals match. Either one alone is normal and does not flag. Writes approved or needs rework back to the sheet. A flagged row gets the offending past post plus the exact signals that matched, then goes to Slack. Setup Create a Google Sheet with two tabs: Drafts with columns id, text, status, note; and Published with columns text, published_at. Connect your Google Sheets credential on the three Sheets nodes and pick your document. Connect Slack on the last node, or replace it with Telegram, Discord or Gmail. The message is already built for you in the previous node. Put ready in a draft's status column, then activate the workflow. Requirements A Google Sheets credential, and a Slack credential or any other notifier you swap in. No AI model call and no paid API. A record of what you already published, in the Published tab. The repetition check has nothing to compare against without it. Customization Three numbers at the top of the Compare node: WORD_OVERLAP (0.18), STRUCTURE_HITS (2) and HISTORY (30). Raising either of the first two makes the gate quieter. Add your own autopilot phrases to the FILLERS list, and your own ending patterns to endingType. Plain text, no regex needed. Additional info Most duplicate checks compare words, which misses the real problem: you can write thirty posts that share no vocabulary and still feel identical, because every one opens the same way, ends the same way and runs the same rhythm. Readers get bored by the shape, not the nouns. That is why this requires both signals before it flags anything: two posts that merely share a rhythm are not a problem.

Process Stripe refunds with Allowly approval and reviewer checks

Quick overview This workflow runs a Stripe test-mode refund only after an Allowly policy check allows it or a reviewer approves it via a secure callback, then creates the refund in Stripe and fetches the Allowly decision receipt as evidence. How it works Starts manually and builds a refund request containing the Allowly authorization ID, Stripe PaymentIntent ID, amount, currency, reason, and a frozen resource string for approval binding. Validates the request format and reads the Stripe PaymentIntent via the Stripe API to ensure it is a succeeded test payment with sufficient captured funds. Sends the frozen resource and context to Allowly for a refund.create decision check. If Allowly allows immediately, proceeds; if Allowly requires confirmation or escalation, waits for an authenticated HTTP callback with an approval decision and resolves the confirmation/escalation in Allowly before re-checking for a final allow. If the final decision is allow, creates the Stripe refund using an idempotency key tied to the refund request ID. Validates the Stripe refund response and then retrieves the Allowly receipt via the Allowly API to export the refund evidence (marking it pending if not yet signed). Setup Add Stripe API credentials for a Stripe test account and select the same credential for both Stripe HTTP requests. Add Allowly API credentials and select them on all Allowly nodes and the receipt-fetching HTTP request. Create and store an Allowly authorization ID, then replace authorizationId, paymentIntentId, and other fields in the refund request payload as needed (this template only supports USD with reason requested_by_customer). Configure the Wait for reviewer step to require header authentication, then copy its resume webhook URL and send POST reviews in the form {"approved": true|false, "resource": ""} within 4 minutes.

BeginnerManual Trigger

Manage Gemini File Search RAG stores and documents with n8n forms

Quick Overview This workflow creates and manages Gemini File Search RAG stores via an Agents tool, and ingests documents through an n8n Form that uploads files to Google’s Generative Language API for indexing. How it works Receives tool calls from an n8n Chat Agent with fields like action, storeName, documentName, query, and force. Normalizes the tool input and routes the request to the correct operation (list, create, get, query, list documents, delete document, or delete store). Calls the Google Generative Language API to list stores, create a new fileSearchStore, fetch store status, or run a Gemini grounded query against a selected store. Lists documents in a store or deletes a specific document using its documentName when requested. Deletes an entire store only when force is explicitly set, otherwise returns a force-required error message. Separately, an n8n Form trigger accepts file uploads and either creates a new store or targets an existing store, then uploads and imports each file into the Gemini File Search store for indexing. Displays a completion page with the store ID (storeName) to use in the Agents tool for querying and ongoing management. Setup Add Google Gemini (Google PaLM / Generative Language API) credentials in n8n with access to the File Search and Gemini models endpoints. Publish the workflow form and use its public URL to ingest documents, pasting an existing fileSearchStores/... ID when adding to an existing store. Add this workflow as a Tool in your n8n Agent, and ensure the agent sends separate fields (action, displayName, storeName, documentName, query, force) rather than embedding JSON in query. Update any environment-specific values such as pageSize limits or the Gemini model name (gemini-2.5-flash) if your project uses different defaults.

BeginnerManual Trigger

Label AI-generated content for EU AI Act compliance with Slack and Postgres

Quick overview This workflow collects AI-generated assets via an n8n form or sub-workflow call, classifies them for EU AI Act Article 50 disclosure, optionally burns disclosure labels into media, routes each asset through a human approval gate (with optional Slack notification), and records decisions plus a registry snapshot in Postgres. How it works Receives an asset submission from an n8n Form trigger or from another workflow via Execute Workflow. Hashes the prompt, classifies the asset against EU AI Act Article 50 rules, and generates a language-specific disclosure sentence and manifest metadata. For text assets, appends the disclosure sentence to the text when disclosure is required. For media assets, saves the incoming file and attempts to burn in the disclosure label using n8n Edit Image for images or an HTTP media-labelling service for video/audio, falling back to non-burn-in handling if labelling fails. Stores the asset manifest and approval link in Postgres and optionally posts a review request to a Slack channel. Waits for a reviewer to approve, apply an editorial exception (text only), or return the asset, then records the decision in a hash-chained Postgres ledger and snapshots an AI-systems registry by scanning workflows via the n8n API. Setup Create and configure the required Postgres tables/triggers (assets, decisions ledger, and registry snapshots) and add a Postgres credential in n8n. Add an n8n API credential so the workflow can list workflows and generate the registry snapshot. (Optional) Add a Slack credential with permission to post messages and set the target channel for review notifications. (Optional) Deploy and network the media-labelling HTTP service at the configured URL (http://kit-media-label:8881) if you want burn-in labels for video/audio; otherwise those assets fall back to non-burn-in labelling behavior. Requirements Self-hosted n8n: the workflow writes files to disk and reads the instance's own workflows through the n8n API PostgreSQL for the append-only decision ledger and the AI-systems registry; the schema and a docker compose stack that creates it are in the repository A Slack credential with chat:write (and files:write to attach the asset) only if you use the Slack gate; the built-in form gate works without Slack Basic knowledge of which Article 50 obligations apply to you: the template implements the mechanism, it does not give legal advice Customization Edit the nine Article 50 paths and their disclosure sentences in the Classify (Art. 50) node to match your house style and languages Call it from an existing production line with Execute Sub-workflow, passing asset_type, language, model, prompt, operator, depicts_real_person, public_information and the file as binary data Change the Slack channel, or remove the Slack node to run the gate purely as an n8n form Point the Postgres nodes at an existing audit database if you already keep one; the ledger only needs the append-only trigger to stay meaningful Additional info Article 50 of the EU AI Act applies from 2 August 2026, and the deep-fake definition it leans on is Article 3(60). This template is the mechanism rather than the policy: it decides, labels, stops for a person, and leaves a record that can be checked. Full source, the database schema with the append-only triggers, a docker compose install and a written case study: https://github.com/karusrus/transparency-kit and https://karusrus.github.io/transparency-kit/ . Built by Ruslan Karymov, AI Enablement & Automation Lead, Creative, marketing and business operations.

Monitor KPI anomalies with Postgres, Slack, Gmail, GitHub and Claude

Quick overview This workflow collects daily KPIs in Postgres, builds robust baselines, detects anomalies each morning, and then investigates them with an OpenRouter (Claude) agent using Postgres and GitHub tools before routing alerts to Slack, GitHub Issues, and Gmail, plus a weekly precision report. How it works Runs nightly at 01:00 (or manually) to read enabled metric definitions from Postgres, execute each metric’s SQL, and store yesterday’s observation. Recomputes per-metric baselines in Postgres using a 28-day median and MAD (plus day-of-week medians), records baseline coverage, and posts a Slack warning if some metrics lack enough history to be scored. Runs daily at 07:00 to pull yesterday’s KPI values joined with baseline stats and metric metadata from Postgres. Scores each KPI move into a robust z-score, applies direction and minimum-change rules, filters to anomalies, and suppresses duplicates based on recent open incidents and a per-run incident cap. For each admitted anomaly, creates an incident record in Postgres, has an OpenRouter (Claude) agent query Postgres and GitHub for supporting evidence, and discards the explanation if it fails an evidence/consistency check. Updates the incident with the investigation outcome, then routes notifications by severity to Slack (and for critical alerts also files a GitHub Issue and emails the metric owner for acknowledgement). Accepts alert dispositions via a header-authenticated webhook and writes the result back to Postgres, and every Monday sends a Gmail + Slack report summarizing alert precision and recommending z-threshold adjustments. Setup Set up the required Postgres database schema and tables (for example: kpi_metrics, kpi_observations, kpi_baselines, kpi_incidents, and related reporting tables) and populate kpi_metrics with enabled metrics and their metric_sql. Add Postgres credentials for all database steps, Slack access token credentials for alerting, GitHub access token credentials for listing pull requests and creating issues, Gmail credentials for sending emails and approvals, and an OpenRouter credential for the Claude model. Replace placeholders like ALERT_SLACK_CHANNEL and DATA_ONCALL_EMAIL in the workflow’s settings nodes with your real Slack channel(s) and on-call/owner email addresses. If you use the disposition endpoint, copy the webhook URL for the Disposition Webhook, configure its header-auth authentication in your feedback source, and post only the supported dispositions (confirmed, false_positive, wont_fix). Run the nightly collection for at least 14 days (or backfill kpi_observations) so baselines have enough history before expecting anomaly scoring.

Why Choose Us?

AI-Powered n8n Templates

GPT-4 powered intelligent engine that generates custom n8n templates from simple descriptions

Premium Quality n8n Templates

Every n8n template is tested and verified to ensure reliability and practical automation value

One-Click Import

Support one-click import to n8n, start using immediately

Ready to Get Started?

Start using AI to generate n8n templates now, or explore our comprehensive n8n templates library with 7000+ proven workflows

Start AI Generation Browse Templates