Browse 160,118 AI agents

By ibm-granite

granite-4.2-3b-fp8 is an open-weight text-generation model with roughly 3B parameters published by ibm-granite on the Hugging Face Hub. It has 1,433 downloads. Runs with transformers.

By ryugyosoft

granite-4.2-3b-onw is an open-weight text-generation model with roughly 3B parameters published by ryugyosoft on the Hugging Face Hub. It has 1,416 downloads. Runs with onw.

By dealignai

Nanbeige4.3-33B-UNCENSORED-GGUF is an open-weight text-generation model with roughly 33B parameters published by dealignai on the Hugging Face Hub. It has 15,352 downloads.

By ReadyArt

Wicked-Tutu-26B-A4B-Final-GGUF is an open-weight text-generation model with roughly 26B parameters published by ReadyArt on the Hugging Face Hub. It has 2,031 downloads.

By lflare

Qwen3.8-Flash-Next-NVFP4-Abliterated is an open-weight text-generation model published by lflare on the Hugging Face Hub. It has 1,522 downloads. Runs with transformers.

By ReadyArt

Omega-Arsenal-12B-GGUF is an open-weight text-generation model with roughly 12B parameters published by ReadyArt on the Hugging Face Hub. It has 11,588 downloads.

By QuantFactory

stable-code-instruct-3b-GGUF is an open-weight text-generation model with roughly 3B parameters published by QuantFactory on the Hugging Face Hub. It has 2,486 downloads. Runs with transformers.

By jackasda211233

Qwen3.5-27B-Uncensored-RYS-Reasoner-GGUF is an open-weight text-generation model with roughly 27B parameters published by jackasda211233 on the Hugging Face Hub. It has 2,205 downloads.

By Nanbeige

Nanbeige4.3-33B is an open-weight text-generation model with roughly 33B parameters published by Nanbeige on the Hugging Face Hub. It has 7,412 downloads. Runs with transformers.

By abenzerps

Nanbeige4.3-33B-GSQ-RCO-GGUF is an open-weight text-generation model with roughly 33B parameters published by abenzerps on the Hugging Face Hub. It has 10,777 downloads. Runs with gguf.

By PollardWeights

NVIDIA-Nemotron-3.5-Bolt-E4B-Pollard is an open-weight text-generation model with roughly 4B parameters published by PollardWeights on the Hugging Face Hub. It has 6,031 downloads. Runs with gguf.

By nesymerp1

Nanbeige4.3-33B-Base-Q4_K_M-GGUF is an open-weight text-generation model with roughly 33B parameters published by nesymerp1 on the Hugging Face Hub. It has 3,689 downloads. Runs with transformers.

By bartowski

PocketDoc_Dans-PersonalityEngine-V1.2.0-24b-GGUF is an open-weight text-generation model with roughly 24B parameters published by bartowski on the Hugging Face Hub. It has 5,167 downloads.

By haoranxu

Llama-3-Instruct-8B-SimPO is an open-weight text-generation model with roughly 8B parameters published by haoranxu on the Hugging Face Hub. It has 8,587 downloads. Runs with transformers.

By sbintuitions

sarashina2.2-3b-instruct-v0.1 is an open-weight text-generation model with roughly 3B parameters published by sbintuitions on the Hugging Face Hub. It has 13,517 downloads.

By mobilint

EXAONE-4.0-1.2B is an open-weight text-generation model with roughly 1.2B parameters published by mobilint on the Hugging Face Hub. It has 27,432 downloads. Runs with transformers.

By trl-internal-testing

tiny-Phi3ForCausalLM-3.5 is an open-weight text-generation model published by trl-internal-testing on the Hugging Face Hub. It has 22,961 downloads. Runs with transformers.

By bartowski

Nanbeige_Nanbeige4.3-33B-GGUF is an open-weight text-generation model with roughly 33B parameters published by bartowski on the Hugging Face Hub. It has 73,041 downloads.

By ibm-granite

granite-4.2-30b is an open-weight text-generation model with roughly 30B parameters published by ibm-granite on the Hugging Face Hub. It has 40,121 downloads. Runs with transformers.

By mikeinnyc

Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16 is an open-weight text-generation model with roughly 27B parameters published by mikeinnyc on the Hugging Face Hub. It has 34,687 downloads. Runs with transformers.

By patrickbdevaney

GLM-5.3-Flash-REAP50-GGUF is an open-weight text-generation model published by patrickbdevaney on the Hugging Face Hub. It has 33,475 downloads. Runs with gguf.

By AtomicChat

Qwen3.5-4B-DFlash-GGUF is an open-weight text-generation model with roughly 4B parameters published by AtomicChat on the Hugging Face Hub. It has 26,947 downloads. Runs with gguf.

By FengZhenfei

Ontology-Augmented Generation for AI agents. An open-source AI framework/SDK by FengZhenfei, hosted on GitHub.

By busabase

Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable. An open-source AI framework/SDK by busabase, hosted on GitHub.

By dagoSte

Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits. An open-source AI framework/SDK by dagoSte, hosted on GitHub.

By karust

Self-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉. An open-source AI framework/SDK by karust, hosted on GitHub.

By michaelshimeles

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex. An open-source AI framework/SDK by michaelshimeles, hosted on GitHub.

By mmalmi

Private mesh VPN for humans and agents. Local keys, signed enrollment, no provider account. Native apps and CLI. An open-source AI framework/SDK by mmalmi, hosted on GitHub.

By TYKAIRO-AI

Quick overview This webhook-driven workflow generates short-form video scripts and publishing copy with OpenAI, runs a local copy/duration audit, and renders approved 9:16 videos via Creatomate, returning either a creative kit, an audit checklist, a render job ID, or a final video URL. How it works Receives a POST webhook request (header-authenticated) with an action of draft, audit, render, or status. Validates and sanitizes the request fields, enforcing limits and requiring explicit approval and rights confirmation before rendering. For draft requests, sends a prompt to the OpenAI Chat Completions API to generate two hooks, a 4-scene storyboard, voiceover, hashtags, and SEO metadata, then returns a validated publishing kit for YouTube/TikTok/Instagram. For audit requests, performs a deterministic local preflight to estimate duration and flag copy issues (for example length limits and exaggerated claims) and returns a checklist for human review. For render requests, submits the approved Hook, Supporting_Text, and CTA into a specified Creatomate 1080×1920 template and returns the queued render job ID. For status requests, fetches the Creatomate render job status and returns the final video URL and snapshot URL once the render succeeds (or errors if it fails). Setup Create a header-authenticated webhook credential for the incoming request and configure the calling app to send the required header. Add an OpenAI API key as an HTTP Header Auth credential for the OpenAI request step. Add a Creatomate API key as an HTTP Header Auth credential for the Creatomate render and status request steps. In Creatomate, create a 1080×1920 template and ensure it contains elements named exactly Hook, Supporting_Text, and CTA, then use its template_id in render requests. Build your client request payloads for each action (draft/audit/render/status) and only call render with approved=true and rights_confirmed=true after a manual review. An n8n automation workflow template by TYKAIRO-AI.

By toshiyuki kikuchi

Quick overview Audits only changed Figma frames against your design system: contrast, font size, tap targets, unlinked tokens and detached components. A Gemini agent reviews each screenshot with your design guide. New issues become Figma comments, fixed ones get a ✅ reply, and Slack gets summaries and weekly reports. How it works Triggers when a Figma named version is saved via webhook, when someone submits the audit request form, or every Monday at 9:00. Validates the request (including the Figma webhook passcode), loads the design guide from Google Docs, and fetches the Figma file structure. Selects the target page, lists top-level frames, compares frame fingerprints against the stored snapshots in n8n Data Tables, and keeps only frames that changed (or forces a review for form requests). For each changed frame, runs deterministic checks on the Figma node tree for contrast, font size, tap targets, token/style usage, and possible detached components, then loads any still-open findings for that frame. Exports a PNG screenshot from Figma and sends it, the layer index, the design guide, and open issues to a Google Gemini agent that proposes new issues and marks previously reported AI issues as resolved when they appear fixed. Reconciles new, still-open, and fixed findings by pinning new comments in Figma, replying in existing threads for fixed items, and updating the findings and frame snapshots in n8n Data Tables. Posts an audit summary to a Slack channel after each run and posts a weekly design-health report to Slack based on the stored findings and frame metrics. Setup Create a Figma personal access token with access to read file content and write comments, and configure it as HTTP Header Auth for all Figma API requests (including the layer-inspection tool) and set a webhook passcode. Add Google Docs OAuth credentials for reading your design guide and update the design guide document URL in the workflow configuration. Add a Google Gemini API credential for the Gemini chat model used by the agent. Add Slack credentials and set the target channel ID in the workflow configuration. Update the workflow configuration values (page name, review focus, thresholds, limits, and timezone), and if using the Figma trigger, register a Figma FILE_VERSION_UPDATE webhook pointing to the production webhook URL with the same passcode. Requirements Figma account with a personal access token (file content read, comments write) Google Gemini API key Google account with the design guide in Google Docs Slack workspace with a bot (chat:write) invited to the target channel n8n with Data Tables (n8n Cloud or a recent self-hosted version) Customization Change contrast, font size and tap-target thresholds or the per-run limits in Workflow Configuration Set reviewLanguage to get Figma comments in another language Add your own rules in Run Design Checks; new rules are tracked and closed automatically like the built-in ones Replace the Slack nodes with Gmail or Microsoft Teams, or move the weekly report to another day Additional info Tested end to end on a Figma file with color variables, text styles, a component and a detached copy. On the second run, fixed issues received a "✅ Fixed" reply and reaction in their original comment threads, and unchanged frames were skipped. An n8n automation workflow template by toshiyuki kikuchi.

By Yuji

Quick Overview This workflow checks the Japan Meteorological Agency (JMA) weather warning feed every 30 minutes, compares changes per watched prefecture, posts alerts and an approval form to Microsoft Teams, and (after approval) emails affected customers via Gmail while tracking shipment and warning state in n8n Data Tables. How it works Runs every 30 minutes and loads workflow settings plus the saved warning state and open shipments from n8n Data Tables. Downloads the public JMA XML warning feed, posts an error card to Microsoft Teams if the feed request fails, and otherwise parses the feed. Filters feed entries to the watched prefectures, keeps the newest entry per prefecture, fetches each entry’s detail XML, and extracts the active warning types and headline. Compares the current warnings to the previously saved warnings per prefecture, routes only newly issued/changed warnings and all-clear events, and upserts the latest state back to the warning state table. For newly issued warnings, matches the affected prefecture (and the warehouse prefecture) against pending shipments due within the lookahead window in the open shipments table. Uses OpenAI to draft a Japanese internal alert plus a polite customer email template with placeholders, then posts the alert to Microsoft Teams and, if shipments are affected, posts a Teams card with a “Review and send” link to an n8n approval form. Waits for staff to approve or skip sending (with a reminder and expiry if no response), then sends one Gmail email per affected order and updates each order record with the send result and posts a send summary to Microsoft Teams. Setup Create two n8n Data Tables named weather_alert_state (prefecture, warnings, reported_at) and open_shipments (order_id, customer_name, email, ship_to_prefecture, ship_date, status, notice_sent, notified_at) and populate open_shipments with your pending orders. Add an OpenAI credential (Chat model) and a Gmail OAuth2 credential for the mailbox that sends customer notices. Configure a Microsoft Teams Workflows/Incoming Webhook URL and paste it into the teams_webhook_url setting, then update watched prefectures, warehouse prefecture, lookahead days, reminder timing, and company signature in the settings node. An n8n automation workflow template by Yuji.

By Onur Olgun

Quick overview This workflow provides a Gemini Live assistant for an e-commerce store by generating single-use Gemini ephemeral tokens, loading a knowledge base from a Google Drive folder, and handling tool calls to read order status, create return/exchange requests, log complaints to Google Sheets and notify the owner via Gmail How it works Receives a POST webhook request to create a new Gemini Live voice session. Applies daily and per-IP rate limits, then lists and downloads supported knowledge files from a specified Google Drive folder and combines them into a single system prompt. Builds a Gemini Live session configuration (voice, model, and tool schema), signs the session with an HMAC, and requests a single-use ephemeral token from the Gemini API. Returns the token, model, WebSocket URL, signed session metadata, and tool-callback URL to the client via the webhook response. Receives tool-call webhook requests from the Gemini Live client, validates the HMAC signature and expiry, and enforces a per-session tool-call limit. For authorized tool calls, reads order data from Google Sheets to return order status, verifies and appends return/exchange requests to Google Sheets and emails the owner, logs complaints to Google Sheets and emails the owner, or sends owner notifications for unanswered questions. Responds to the tool-call request with a JSON result (or returns an error for missing info, rate limits, unknown tools, or unauthorized calls). Setup Add an HTTP Header Auth credential containing your Gemini API key with header name x-goog-api-key. Connect Google Drive OAuth2, Google Sheets OAuth2, and Gmail OAuth2 credentials used by the workflow. Update the Business Settings values, including owner email, Google Drive folder ID, Google Sheet ID, public tool URL, and a long random HMAC secret. Create or update the Google Sheet with tabs and columns for Siparisler, Iadeler, and Sikayetler matching the fields the workflow reads/writes. Copy the production webhook URLs for /webhook/gemini-live-token and /webhook/gemini-live-tool into your client application and restrict allowedOrigins on both webhooks to your site domain. An n8n automation workflow template by Onur Olgun.

By Pushbuild

Quick overview This workflow receives new lead submissions via a webhook, normalizes the data, scores the lead with OpenAI, sends an acknowledgment email, upserts the contact into HubSpot, and posts a Slack alert when the score meets a configured “hot lead” threshold. How it works Receives a POST request on a webhook endpoint whenever a new lead is submitted. Normalizes incoming form fields into a consistent lead object (name, email, phone, company, message, source) and prepares an OpenAI Chat Completions request. Sends the lead details to the OpenAI API to generate a 1–10 score plus a short reason and summary in JSON. Parses the OpenAI response and attaches the score, reason, and summary to the lead record. Sends a thank-you email to the lead using your SMTP mail server with a booking link for follow-up. Upserts the lead as a contact in HubSpot using the email address as the unique identifier. Posts a message to Slack via an incoming webhook when the lead score is greater than or equal to the configured hot-lead score. Setup Configure the webhook URL in your form tool to POST lead submissions to the workflow’s “New lead” production webhook endpoint. Add an HTTP Header Auth credential for OpenAI (Authorization: Bearer ) and attach it to the OpenAI request. Add an HTTP Header Auth credential for HubSpot (Authorization: Bearer ) and attach it to the HubSpot upsert request. Add an SMTP credential for sending email and set the from address, business name, booking link, Slack incoming webhook URL, and hot-lead score in the Config values. An n8n automation workflow template by Pushbuild.

By LatentLark

Quick overview This workflow runs weekly (or manually) to scrape Google Maps leads via Apify, audits each business website with LatentLark Local Lead Audit to generate issues and outreach angles, and appends the enriched lead data to a Google Sheets spreadsheet. How it works Runs every Monday at 08:00 (or starts from a manual test run) and loads the search term, location, maximum places, and campaign key. Uses Apify’s Google Maps Scraper actor to collect matching businesses from Google Maps based on the configured search and location. Sends the scraper run’s dataset to Apify’s LatentLark Local Lead Audit actor to audit each website, attempt to find owner/contact details, and generate a pitch angle and email opener while skipping previously seen businesses. Drops results flagged as error, invalid input, or skipped, and keeps only valid business records. Maps the audit output into a consistent set of columns (business details, issues, scores, and outreach fields) and appends each row to Google Sheets. Setup Install the Apify community node (@apify/n8n-nodes-apify) if needed and add an Apify API token credential. Create a Google Sheet with header columns that match the workflow’s output (for example: businessName, website, city, phone, email, ownerName, problemScore, grade, primaryIssue, issues, pitchAngle, emailOpener, rating, reviewCount, mapsUrl, auditedAt). Add Google Sheets OAuth2 credentials and select the target spreadsheet and sheet/tab in the Google Sheets append step. Update the Settings values (searchTerm, location, maxPlaces, and a unique campaignKey used to deduplicate with onlyNew), then run once manually before enabling the weekly schedule. An n8n automation workflow template by LatentLark.

By Christian

Quick overview This workflow runs on a schedule or manually to update WordPress plugins and themes over SSH using WP-CLI, verifies site health with HTTP checks and log inspection, automatically rolls back breaking updates, and emails an HTML report with optional Groq AI analysis of failures. How it works Copy selfheal.sh from the GitHub repository (github.com/Christianzimpel/n8n-wp-self-healing-update-agent) to ~/wp-selfheal/selfheal.sh on your server. Provide an SSH private key credential with access to the WordPress server and make sure the server has WP-CLI, PHP CLI, tar, and curl available. Connects to the server via SSH, checks that the helper script is installed, backs up the database, enables temporary debug logging, and fetches the list of available plugin and theme updates. If no updates are available or the preparation step fails, sends an email indicating everything is up to date or that the run was aborted. Processes each plugin and theme update one at a time over SSH by backing up the component, running the WP-CLI update, and building one or more URLs to check. After each update, requests the configured site paths over HTTP and checks via SSH whether WordPress boots and whether new PHP fatal errors appear, then marks the update as successful or schedules a rollback. If the site appears broken, restores the plugin/theme from its backup over SSH, and if rollback fails, stops further updates and sends an emergency email. After all items (including a retry round for previously rolled-back/failed items), restores debug settings, optionally sends failure logs to Groq for analysis, and emails a consolidated HTML report. Setup Provide an SSH private key credential with access to the WordPress server and ensure the server has WP-CLI, PHP CLI, tar, and curl available. Update the Configuration values for siteUrl, wpPath, wpCli, and checkPaths, and (optionally) set phpErrorLog, keepDays, and maxAttempts to match your environment. Add an SMTP/email credential and set the mailTo and mailFrom addresses used for the report, no-updates notice, aborted-run notice, and emergency alert. Add a Groq credential (or replace the Groq model with another supported chat model) if you want AI-generated analysis included in the report. Verify the schedule in the Monday 4 AM trigger (or disable it) and run the workflow manually against a staging site before enabling it in production. An n8n automation workflow template by Christian.

By AI Agent Starter Kit

Quick overview This workflow runs every weekday morning, pulls today’s Google Calendar events and recent unread Gmail messages, uses an OpenAI-compatible chat completions API to write a short plain-text briefing, and emails the briefing to you via Gmail. How it works Runs every weekday at 7 AM (or on-demand via a manual trigger for testing). Reads your settings (timezone, goal, inbox search, model, and email recipient) and fetches today’s events from Google Calendar. Queries Gmail for unread inbox emails from the last 24 hours using your configured Gmail search filter. Cleans and summarizes the raw data by sorting meetings, flagging back-to-back events, calculating total meeting time and your longest free focus block, and trimming each email to sender/subject/snippet. Sends the prepared calendar and email context to an OpenAI-compatible API endpoint to generate a three-part briefing (TODAY, INBOX, ONE THING) under the configured word limit. Formats the final email body using the AI response or a fallback plain list if the AI request fails, then sends it to your address through Gmail. Setup Add Google Calendar OAuth2 credentials and select them for the calendar-read step, ensuring the calendar ID matches the calendar you want to summarize. Add Gmail OAuth2 credentials and select them for both reading unread emails and sending the briefing email. Add an HTTP Header Auth credential for your LLM provider (Authorization: Bearer YOUR_API_KEY) and set the LLM base URL and model to match your OpenAI-compatible endpoint. Update the workflow settings values (recipient email, timezone, goal, inbox search, and workday hours) to match your preferences, then test with the manual trigger before activating the schedule. An n8n automation workflow template by AI Agent Starter Kit.

By Zhang Lixiang

Quick overview This workflow handles WhatsApp Business Cloud API webhooks, verifies the callback URL, and replies to incoming WhatsApp text messages using keyword-matched FAQs with an OpenAI fallback that can only select from approved FAQ IDs before sending the stored answer back via WhatsApp. How it works Receives a GET request from Meta to verify the WhatsApp webhook and returns the hub.challenge only when the provided verify token matches. Receives WhatsApp webhook POST events and keeps only incoming text messages while ignoring delivery/read receipts. Scores each message against a built-in FAQ list using keyword matching and selects the highest-scoring FAQ answer when a match is found. If no keyword match is found, sends the customer message plus the FAQ IDs and questions to an OpenAI chat model to choose a single FAQ ID or null. Validates the model’s output against the known FAQ IDs and selects either the corresponding stored answer or a fixed fallback message. Sends the chosen reply back to the customer via the WhatsApp Business Cloud API using the same phone number that received the message. Setup Create a Meta app with the WhatsApp product, connect a business phone number, and configure webhook subscriptions for messages. In n8n, add WhatsApp Business Cloud API credentials and an OpenAI (or OpenAI-compatible) credential for the chat model node. Replace YOUR_VERIFY_TOKEN in the webhook verification check and use the same token in Meta’s webhook settings. Activate the workflow and copy the production webhook URL for the whatsapp-faq path into Meta’s webhook configuration. Edit the FAQ list (IDs, questions, keywords, answers) and update placeholders like YOUR_BOOKING_LINK and the fallback message to match your business. Additional info Need signature verification, deduplication, opt-out handling and human handoff? A production version is available at https://zhangautomation.gumroad.com/l/ecvlr. An n8n automation workflow template by Zhang Lixiang.

By Advisync

Quick overview Inspect bounded Vinted listing samples, then preview rows or a short summary for Google Sheets, Slack, Notion or email. Choose Ralph Lauren, Dior, Sezane or a custom search. The default first execution prepares input without credentials, source requests or destination writes. How it works A manual trigger reads eight common customer fields; a separate Advanced controls node retains source modes, approval phrases and lowerable resource ceilings. With no completed run ID, AUTO prepares the selected search and returns a readable configuration receipt without HTTP, credentials or writes. A matching completed run ID selects recovery; AUTO never starts a paid search. For listing previews, three Apify read nodes verify the exact Actor/build, terminal status, original stored input, resource and cost guards, then validate the versioned results payload. The workflow removes exact duplicate source rows, preserves partial/capped warnings and prepares full listing receipts for Sheets or a bounded digest for the other destinations. Asking prices do not establish sale value or profit. PREVIEW displays the selected target and proposed content, then stops before every destination writer. A separate explicit approval is required for any write or delivery. The Sheets path reads before writing, appends missing observation receipts, verifies them and writes the run completion marker last. An exact completed replay is designed to skip duplicate writes. Slack, Notion and email use a durable n8n Data Table intent before one provider call and verify the provider receipt. Unresolved attempts stop for manual reconciliation. Run executions serially: the journal does not guarantee concurrent exactly-once delivery. Setup Import into a new empty workflow and keep manual execution. Open node 01, choose one preset and destination, and leave the completed run ID blank. Execute once and read node 02B. No credential is required for this first configuration check. To preview actual listings, supply your own matching completed Actor 0.13.69 run ID and one destination target. A standard Google Sheets or Notion page link is accepted; Slack uses one channel ID, and email uses one sender and recipient. For recovery, select your own Apify Bearer Auth credential only on read nodes 04B, 07A and 08A. Leave paid-start node 04A unbound. Keep Advanced write_mode=PREVIEW and inspect the target, proposed content and partial-result warnings. For later Sheets writes, create Vinted Listings and Vinted Runs tabs with the exact headers in the canvas note, then connect your Google Sheets credential to the listed Sheets nodes. Use the Advanced write controls only after reviewing a preview. For later Slack, Notion or SMTP delivery, connect only the selected service credential and create the n8n Data Table with the exact string columns in the recovery note. Set its ID and the destination-specific approval phrase in Advanced controls. Starting a new Actor run is optional and separate: explicitly choose START_BOUNDED_RUN, bind 04A and enter its exact approval phrase. The fixed ceilings are USD 0.25, 40 listing rows and 45 total source requests. Reuse completed runs for recovery instead of starting another collection. Requirements n8n with Manual Trigger, Set, Code, If, HTTP Request and the selected service nodes; Data Table is needed for Slack/Notion/email delivery. An Apify account and your own credential are needed only when retrieving or starting a source run. This template fixes source build 0.13.69 and payload contract 0.13.0. Use customer-owned service credentials and one exact destination. No owner credentials or real destination IDs are embedded. Customization Choose one of three presets, or select custom and set query, optional size and maximum asking price in node 01. Simple custom searches default to buyer/France; goal and countries remain editable in Advanced. Paste the selected destination link or ID into destination_target. Conflicting common and Advanced targets stop before HTTP. Other destination targets are cleared from the resolved configuration. Lower resource ceilings in Advanced. Keep previews enabled until the proposed rows or digest and its exact target have been reviewed. Additional info This unofficial Actor supports listing inspection, not purchases, sold-price estimates, seller-country identification or profit forecasts. France has bounded source-validation evidence; broader reliability is unproven. Partial/capped results must remain visibly partial. Source cost controls are requested ceilings; platform settlement can slightly exceed them. Native compact configuration preparation was verified in n8n Cloud; actual listing preview and each provider delivery for this exact revision remain separate qualification gates. Provider acceptance does not prove recipient delivery or reading. Keep executions manual and serialized; reconcile unresolved journal attempts rather than blindly resending. An n8n automation workflow template by Advisync.

By Le Thua Phu

Quick overview This workflow reads URLs from Google Sheets, checks each page for noindex directives in the meta robots tag or X-Robots-Tag header, writes the status back to the sheet, and for rows marked “Needs index” calls the RankMath WordPress REST API to switch robots settings to index. How it works Starts manually and loads URL rows from a Google Sheets tab, focusing on rows that match the configured filter. Processes the URLs in batches, fetching each page over HTTP and parsing the HTML and headers for meta robots and X-Robots-Tag values. Writes the detected robots status (for example NOINDEX, INDEX, noindex via header, no meta robots found, or an HTTP error) back to the Google Sheet. After the check completes, reads the rows where the Google Sheet “Note” column equals “Needs index.” Fetches each marked page again and extracts the underlying WordPress post or term ID from headers or page markup, while preparing a new robots value that replaces noindex with index. Sends the updated robots meta to the RankMath updateMeta REST endpoint in WordPress for rows with a valid object ID and records API errors for the rest. Updates the Google Sheet with the final result (INDEX or an error status) for each processed row. Setup Create a Google Sheet with a tab named “All URLs” and columns named exactly: URL, Robots Tag, Note. Add your Google Sheets credential in n8n and replace YOUR_GOOGLE_SHEET_ID in all Google Sheets nodes with your spreadsheet ID. Add a WordPress API credential (for example using an Application Password) with permission to edit content, and replace https://your-site.example.com in the RankMath request with your WordPress site URL. Ensure RankMath is installed and its REST API is reachable, then mark rows you want switched by setting Note to “Needs index.” Optionally enable the disabled test limiter to run a small subset first, and avoid sorting the sheet while the workflow is running so row matching stays consistent. Requirements Google Sheets account with OAuth2 credential WordPress site with the RankMath SEO plugin active WordPress user that can edit posts, with an Application Password recommended Network access from n8n to your site Customization Change the Needs index text in Get Rows Needing Index to use your own marker Adjust the filter in Get URLs to check only the rows you want Raise or lower the batch size and interval in the Fetch nodes to suit your server Replace Run Check with a Schedule Trigger for regular checks Adjust the robots values in Get Object ID, which keeps nofollow-type tags and replaces noindex with index Additional info The status INDEX means RankMath accepted the request, not that the page is confirmed indexable. Clear your cache and run the check again to verify. If your site still shows noindex after a run, compare the request body in the RankMath updateMeta node with the request your RankMath editor sends. Pages that expose no post or term ID get the status missing object_id and must be handled manually. Noindex can also come from an X-Robots-Tag header or another plugin, which this workflow cannot change. An n8n automation workflow template by Le Thua Phu.

By Jessy Mariau

Quick overview This workflow runs every weekday at 09:00, reads overdue invoices from a Google Sheets spreadsheet, sends staged payment reminder emails via Gmail at 3, 7, and 14 days past due, then updates the invoice tracking fields and appends an audit entry to a Log sheet. How it works Runs every weekday at 09:00 on a schedule. Loads reminder settings (cadence days, minimum gap between reminders, and a per-run safety cap) and reads all rows from the Google Sheets “Invoices” tab. Selects invoices that are overdue by the next configured reminder day, skips closed/paid statuses, validates required fields (email, amount, due date), and avoids reminding customers too frequently. Builds a personalized email subject and body (including an optional payment link) and sends the reminder through Gmail. Updates the matching invoice row in Google Sheets with the new status, attempts count, last reminder date, and computed next reminder date. Appends a row to the Google Sheets “Log” tab for each successfully sent reminder. Setup Connect a Gmail account/credential that is allowed to send reminder emails. Connect Google Sheets credentials and paste your spreadsheet URL into the Google Sheets nodes that read, update, and log data. Ensure your spreadsheet includes an “Invoices” tab with columns used by the workflow (at minimum: invoice_id, customer_email, customer_name, amount, currency, due_date, status, attempts, last_reminder_at, next_reminder_at, invoice_link) and a “Log” tab with matching log columns. In “Your Settings”, set your display name and adjust reminder_days, min_gap_days, and max_per_run as needed, and leave test_today blank for production use. An n8n automation workflow template by Jessy Mariau.

By Muhammad Firaz Al Aqib

Quick overview This workflow tracks competitor product prices, promos, and stock using MrScraper, logs results to Google Sheets, generates short insights with Google Gemini, and posts Slack alerts only when significant changes occur, running daily on a schedule or on demand via a webhook. How it works Runs daily on a schedule or starts via a POST webhook request and normalizes the input to choose a tracking mode (sheets watchlist, a listing page, or a SERP query). In watchlist mode, reads SKUs from Google Sheets (Watchlist) and the prior run data (History), then scrapes each competitor product page with MrScraper. Compares the scraped competitor price, promo, and stock status to your price and the most recent History entry, appends the new result to the History sheet, and flags meaningful changes. When a change triggers an alert, Google Gemini writes a short recommendation and the workflow posts a detailed Slack alert for that SKU. In listing/SERP mode, uses MrScraper to collect multiple offers (from a category page or from Google results followed by product page scraping), compares each offer to your price, and appends results to the Market History sheet. If any market offers cross the alert rules, Google Gemini summarizes the market position and the workflow posts a single Slack “Market Price Check” summary; webhook runs also return the final results as JSON. Setup Create credentials for MrScraper, Google Sheets OAuth2, Google Gemini (PaLM) API, and Slack (access token). Create a Google Sheet with tabs named Watchlist, History, and Market History, and add Watchlist columns for sku, product_name, my_price, currency, competitor_url, and threshold_pct. Paste your Google Sheet ID and Slack channel ID into the workflow’s Setup values. If using the webhook mode, copy the production webhook URL from n8n and send POST requests to /webhook/competitor-tracker with a valid body (source: sheets, listing, or serp plus the required fields). An n8n automation workflow template by Muhammad Firaz Al Aqib.

By iamvaar

Quick overview Youtube Video: https://youtu.be/0lc_UfiqvIA This workflow collects refund requests via an n8n Form, validates the order in Shopify, save contact to Klaviyo and Shopify journey data, checks images with Sightengine, and uses Gemini to generate fraud triage decision that is logged to Sheets, filed in Jira, and posted to Slack. How it works Receives a refund request through an n8n Form with order details, reason, and an optional image attachment. Writes the submission to Google Sheets with a PENDING_TRIAGE status, then looks up the order in Shopify and checks that the order exists and the submitted email matches. If the order cannot be verified, updates the Google Sheets row with an invalid status and sends an alert to Slack. If the order is verified, looks up the customer in Klaviyo and creates a profile if one does not already exist. Fetches recent order history and customerJourneySummary data from Shopify GraphQL and builds a single AI context payload that also preserves the uploaded image. Sends the attachment to Sightengine’s GenAI detector, converts the result into an authenticity status and score, and passes everything to Google Gemini to produce a structured refund recommendation, fraud risk score, and notes. Creates a Jira issue with the AI triage report, updates the original Google Sheets row with the decision and Jira key, and notifies the support team in Slack. Setup Create and publish the n8n Form, then share its public URL with customers or embed it where you collect refund requests. Connect Shopify OAuth2 credentials and ensure the workflow can access both the Admin REST API (order lookup) and Admin GraphQL API (customerJourneySummary query). Add Google Sheets service account credentials and update the spreadsheet ID and the “Refund Requests” sheet name/columns to match your document. Add Slack credentials and set the target channel(s) for unverified-order alerts and triaged-refund notifications. Add Jira Software Cloud credentials and select the target project and issue type for refund tickets. Add Klaviyo API credentials and configure the account that should own/track customer profiles, and provide Sightengine API credentials for the image authenticity check. An n8n automation workflow template by iamvaar.

By Mohamed Ayoub Jabane

Quick overview This workflow monitors an Unraid server via its GraphQL API, scanning new syslog warnings every minute and running broader health checks every five minutes, then sends deduplicated alerts with suggested next steps to a Telegram chat, with optional Unraid notifications and container auto-restarts. How it works Runs on two schedules: every minute for syslog monitoring and every five minutes for health checks. Calls the Unraid GraphQL API to fetch either only the newly appended syslog lines or a full health snapshot (array, disks, SMART, Docker, notifications, CPU/memory). Classifies syslog lines and health findings by severity and generates actionable alert details and suggested next steps. Normalizes alerts and throttles repeats using stored state so the same issue is only sent once per configured time window. Optionally sends the alert text to a connected chat model for short triage guidance and appends it to the alert. Sends the formatted alert to Telegram, and optionally mirrors it into Unraid’s notification system and auto-starts stopped autostart Docker containers before reporting the result back to Telegram. Setup Create an Unraid admin API key (Unraid Settings → Management Access → API Keys) and configure an HTTP Header Auth credential that sends it as header name x-api-key. Add a Telegram bot credential and set the target chat ID in cfg.telegramChatId. Update cfg.unraidUrl to your Unraid WebGUI base URL (HTTPS) and adjust alert options like cfg.minSeverity and cfg.throttleMinutes. (Optional) Enable cfg.alsoUnraidNotification to create Unraid notifications and/or cfg.autoRestartContainers to auto-start stopped autostart containers. (Optional) Connect a chat model to the AI triage step and enable it if you want AI-generated guidance included in alerts. An n8n automation workflow template by Mohamed Ayoub Jabane.

By Divyanshu Gupta

Quick overview Run school admin from one Telegram chat. Teachers report absences and the bot asks free teachers to confirm cover. The principal approves AI-written English and Hindi circulars before parents are emailed, and gets a daily 8am briefing on attendance, fees and substitutions. Everything is logged in Google Sheets. How it works Triggers when a message arrives in Telegram or every day at 8am via a schedule. Looks up the sender in Google Sheets (Users and Teachers) to determine their role, and replies with a registration message if the chat ID is unknown. Uses DeepSeek to extract the request intent (absence or announcement) and key details from the Telegram message, then routes the request accordingly or sends a help reply. For absence requests, reads the Timetable and existing Substitutions from Google Sheets, ranks available teachers, and sends Telegram approval prompts to the top candidates per period, escalating to the principal when no one accepts. Logs confirmed and uncovered periods to the Substitutions sheet in Google Sheets and sends a consolidated cover-plan summary to both the requester and the principal on Telegram. For announcement requests (Principal/Admin only), uses DeepSeek to draft an English and Hindi circular, asks for Telegram approval, then emails matching parents via Gmail using addresses from the Students sheet and logs the send to the Circulars sheet. At 8am, reads Students and Substitutions from Google Sheets, calculates attendance/fees/substitution counts, uses DeepSeek to write a formatted briefing, and sends it to the principal on Telegram. Setup Create a Telegram bot and add a Telegram API credential in n8n, then message the bot from each staff account and record their Telegram Chat IDs in the Teachers and Users sheets. Connect Google Sheets OAuth2 credentials and update the sheet ID, tab names, and required columns in the Workflow Config and Google Sheets nodes (Teachers, Users, Students, Timetable, Substitutions, Circulars). Add a DeepSeek API credential and ensure it is selected for the information extraction, circular drafting, and daily briefing steps. Add a Gmail OAuth2 credential and update the Gmail “Send To” field to use the recipient email from Google Sheets (or your preferred target) before enabling parent emails. Set the principal’s Telegram Chat ID in the Users sheet (Role = Principal) and adjust Workflow Config values like attendance threshold, due-soon window, and approval wait time to match your school process. An n8n automation workflow template by Divyanshu Gupta.

By MEKA

Quick overview Monitor new public LinkedIn jobs in Google Sheets with MEKA. The workflow validates a focused search, deduplicates job IDs against your sheet, and appends only unseen roles. How it works Use the Manual Trigger for a supervised test, or enable the included daily Schedule Trigger after setup. Read and validate search, spreadsheet, result, and budget settings before starting one MEKA Actor run through Apify. Handle READY and RUNNING responses with a bounded poll loop without retrying the billable start request. Read the Actor OUTPUT summary before accepting data; stop on failed searches and mark enrichment failures or budget stops as partial coverage. Fetch one bounded Dataset batch and normalize valid public LinkedIn job records into the documented ten-column shape. Read existing IDs from the target sheet and remove jobs already present or duplicated inside the fetched batch. Append only unseen rows, preserve firstSeenAt, and report fetched, new, appended, skipped, and coverage counts. Setup Import the workflow JSON and keep it inactive. Create a Google Sheet with a Jobs worksheet and add these exact headers in row 1: id, title, company, location, postedAt, url, salary, employmentType, seniority, firstSeenAt. Create an HTTP Header Auth credential. Set the header Name to Authorization and Value to Bearer . Select the same credential on Start Actor, Poll Actor Run, Get Run Output, and Get Dataset Items. In Search settings, enter your spreadsheet document ID and sheetName, then choose keywords, location, date window, limit, and budgetUsd (mapped to the maxTotalChargeUsd HTTP query parameter). Connect Google Sheets OAuth2 to Read Existing Jobs and Append Rows. Open Workflow settings -> Timezone and choose the timezone you intend to use. Confirm that 08:00 is the intended time in the timezone you explicitly choose. Run the Manual Trigger, inspect the execution and real sheet, and enable the Schedule Trigger only after that test succeeds. Requirements Use n8n with an Apify account and token, a Google account that can authorize Google Sheets OAuth2, and a writable spreadsheet with the documented Jobs worksheet and ten headers. This template is free, but Apify Actor usage may incur separate Apify charges. Customization Edit Search settings to change the keywords, location, date window, result limit, spending cap, spreadsheet, or worksheet. After choosing a workflow timezone, adjust the 08:00 schedule if needed. Focused smaller searches are easier to inspect; result limits and budget caps do not guarantee full-market coverage. Additional info The template is free to use, while Apify Actor runs may incur separate Apify charges; the user's n8n plan may also apply. Public repository: https://github.com/meka-im/linkedin-jobs-scraper-examples. MEKA Actor: https://apify.com/meka.im/linkedin-jobs-scraper. Use one workflow and one active writer per sheet because concurrent read-and-append runs can race. Results depend on search ranking, public availability, enrichment outcomes, and result or budget limits, so this workflow does not provide full-market coverage. An n8n automation workflow template by MEKA.

By Aymeric Besset

Quick overview This workflow runs every five minutes to fetch new Mastodon bookmarks and save them to Wallabag, tracking the last processed bookmark ID in an n8n Data Table and checking Wallabag first to prevent duplicate saved URLs. How it works Runs every 5 minutes on a schedule. Reads the last processed Mastodon bookmark ID (min_id) from an n8n Data Table and falls back to a default value on first run. Calls the Mastodon API (/api/v1/bookmarks) with min_id to fetch only newer bookmarks and stops if none are returned. Extracts pagination values (including the newest min_id) from the Mastodon Link response header and stores the updated min_id back to the Data Table. Processes each bookmarked post individually and decides whether to use the link preview card URL or the first non-mention/non-hashtag link in the post (or the post URL if no link is found). Checks in Wallabag whether the chosen URL already exists and, if not, creates a new Wallabag entry with metadata such as title, author, language, content, origin URL, and published date. Setup Install the community node package n8n-nodes-wallabag in your n8n instance. Create a Mastodon access token with the read:bookmarks scope and add it as an HTTP Bearer Auth credential used by the Mastodon HTTP request. Replace YOUR_MASTODON_INSTANCE in the Mastodon bookmarks request URL with your server domain. Create and select a Wallabag API credential for the Wallabag “exists” and “create” operations. Create an n8n Data Table named mastodon_sync_state with string columns source and min_id, and select it in the nodes that read and upsert the sync state. Optionally adjust the DEFAULT_MIN_ID value (0 starts from your oldest bookmarks) and run the workflow once to initialize state before activating it. Requirements ⚠️ Requires the community node n8n-nodes-wallabag and n8n with Data Tables. An n8n automation workflow template by Aymeric Besset.

By Sam

Quick overview Type a topic; this workflow reads web pages found with DuckDuckGo and gives you one HTML file: an overview in which every paragraph cites a source, quotes checked against the pages, news, and optionally videos and pictures. Self-hosted n8n only. How it works A form takes the topic and whether you want videos and pictures (as links, or with thumbnails). A model plans the searches: up to two web queries, one for news and how recent it must be, one for videos and one for pictures. Code checks the plan. An AI agent searches the web with the DuckDuckGo node as its tool, choosing a past day, week, month or year when the topic asks for recent pages, and returns findings with a quote from each page. Code keeps a finding only if its quote is in the text of a page the tools returned, and stops unless at least three points come from at least two sites. The DuckDuckGo node then searches news, videos and images, adds an instant answer and search ideas, with short waits between searches. A vision model only judges whether a thumbnail is safe. A second model writes the overview from the verified points, and a paragraph that cites no source is dropped. A design agent writes the style sheet, and code accepts it only as plain CSS with readable colours. Code builds one HTML file with all text escaped. The form page shows it in a preview with a Download button. If there is no dossier, the page says why. Setup Self-hosted n8n 2.18 or later: install n8n-nodes-duckduckgo-search 32.19 or later under Settings → Community nodes. Searching and reading pages need no API key or account. Add a credential to the chat-model node, OpenRouter model. Any other chat-model node can replace it; choose a model that returns JSON reliably. Activate the workflow, open the form's production URL and type a topic. A run takes one to two minutes and about 5 to 7 DuckDuckGo searches, so leave a few minutes between runs. Keep the form behind n8n login, as it is set here: it makes the node fetch whatever pages a search returns. Requirements Self-hosted n8n only: community nodes cannot be installed on n8n Cloud n8n 2.18 or later, so that links in the preview open in a new tab The community node n8n-nodes-duckduckgo-search, version 32.19 or later An API key for the AI model: OpenRouter by default, or any provider with an n8n chat-model node No API key or account is needed for DuckDuckGo Customization Change how many points and sources are kept (the limits in Verify the findings) or how many searches the agent may make (its prompt and Max Iterations) Choose another region on the search nodes (they are set to wt-wt, no region) Swap the model node for any other chat-model node Keep the waits between searches: DuckDuckGo limits requests per IP address Send the HTML file by email or save it to Google Drive instead of showing it on the form page Additional info Suggested title: "Create a topic dossier as an HTML file with DuckDuckGo". Please do not use "fact-checked" in the title: the workflow checks that each quote is on the page it cites, but it does not fact-check the claims in them, and the result page says so. The AI model is a swappable part (any chat-model node works), so the title names only the search node. The canvas preview does not render community nodes, so the full canvas is in the screenshot at the top of the description. The workflow JSON is submitted as it is in the repository; the AI-generated sticky notes were not used, because the file already has an overview note and section notes that include the community-node install step and the self-hosted-only line. Source and notes: https://github.com/samnodehi/n8n-nodes-duckduckgo/tree/main/docs/examples. An n8n automation workflow template by Sam.

By Finrod Chen

Quick overview This workflow runs every morning, pulls recent items from multiple RSS feeds, uses TypeSafe Jev to score relevance/importance and deduplicate similar headlines, then uses OpenAI to generate a one-line-per-story digest that it sends to Telegram and Gmail and archives to Google Sheets. How it works Runs every day at 8:00 AM. Reads items from the configured RSS feed URLs, normalizes the entries, keeps only recent stories, and skips links already processed in earlier runs. Sends each story’s title and snippet to TypeSafe Jev to score topic relevance, assign an importance rating, and categorize the story. Filters to stories that meet the relevance and importance thresholds, then compares remaining headlines with TypeSafe Jev to detect and merge duplicates about the same event. Sends the final list of top stories to OpenAI to produce a daily headline and a one-sentence summary per story, falling back to RSS snippets if the AI output is invalid. Formats the digest and delivers it to Telegram and Gmail, then appends one row per story to a Google Sheets archive. Setup Add a TypeSafe (typesafe.ai) Bearer token credential and select it for both Jev HTTP requests. Add OpenAI credentials for the chat model used to generate the headline and per-story summaries. Add Telegram bot credentials and set your target telegramChatId in the configuration step. Add Gmail credentials and set the recipient address in emailTo. Add Google Sheets credentials and update sheetUrl and sheetTab to point to your archive spreadsheet and worksheet. An n8n automation workflow template by Finrod Chen.