Telegram and Postgres integration

🤖💬 Smart Telegram AI Assistant with Memory Summarization & Dynamic Model Selection > Optimize your AI workflows, cut costs, and get faster, more accurate answers. 📋 Description Tired of expensive AI calls, slow responses, or bots that forget your context? This Telegram AI Assistant template is designed to optimize cost, speed, and precision in your AI-powered conversations. By combining PostgreSQL chat memory, AI summarization, and dynamic model selection, this workflow ensures you only pay for what you really need. Simple queries get routed to lightweight models, while complex requests automatically trigger more advanced ones. The result? Smarter context, lower costs, and better answers. This template is perfect for anyone who wants to: ⚡ Save money by using cheaper models for easy tasks. 🧠 Keep context relevant with AI-powered summarization. ⏱️ Respond faster thanks to optimized chat memory storage. 💬 Deliver better answers directly inside Telegram. ✨ Key Benefits 💸 Cost Optimization: Automatically routes simple requests to Gemini Flash Lite and reserves Gemini Pro only for complex reasoning. 🧠 Smarter Context: Summarization ensures only the most relevant chat history is used. ⏱️ Faster Workflows: Storing user + agent messages in a single row reduces DB queries by half and saves ~0.3s per response. 🎤 Voice Message Support: Convert Telegram voice notes to text and reply intelligently. 🛡️ Error-Proof Formatting: Safe MarkdownV2 ensures Telegram-ready answers. 💼 Use Case This template is for anyone who needs an AI chatbot on Telegram that balances cost, performance, and intelligence. Customer support teams can reduce expenses by using lightweight models for FAQs. Freelancers and consultants can offer faster AI-powered chats without losing context. Power users can handle voice + text seamlessly while keeping conversations memory-aware. Whether you’re scaling a business or just want a smarter assistant, this workflow adapts to your needs and budget. 💬 Example Interactions Quick Q&A** → Routed to Gemini Flash Lite for fast, low-cost answers. Complex problem-solving** → Sent to Gemini Pro for in-depth reasoning. Voice messages** → Automatically transcribed, summarized, and answered. Long conversations** → Context is summarized, ensuring precise and efficient replies. 🔑 Required Credentials Telegram Bot API** (Bot Token) PostgreSQL** (Database connection) Google Gemini API** (Flash Lite, Flash, Pro) ⚙️ Setup Instructions 🗄️ Create the PostgreSQL table (chat_memory) from the Gray section SQL. 🔌 Configure the Telegram Trigger with your bot token. 🤖 Connect your Gemini API credentials. 🗂️ Set up PostgreSQL nodes with your DB details. ▶️ Activate the workflow and start chatting with your AI-powered Telegram bot. 🏷 Tags telegram ai-assistant chatbot postgresql summarization memory gemini dynamic-routing workflow-optimization cost-saving voice-to-text 🙏 Acknowledgement A special thank you to Davide for the inspiration behind this template. His work on the AI Orchestrator that dynamically selects models based on input type served as a foundational guide for this architecture. 💡 Need Assistance? Want to customize this workflow for your business or project? Let’s connect: 📧 Email: [email protected] 🔗 LinkedIn: John Alejandro Silva Rodríguez

💅 AI Agents Generate Content & Automate Posting for Beauty Salon Social Media 📲 Who Is This For? This workflow is for beauty salons who want consistent, high‑quality social media content without writing every post manually. It also suits agencies and automation builders who manage multiple beauty brands and want a reusable, AI‑driven posting system they can adapt per client. What Problem Is This Workflow Solving? Many beauty businesses struggle to post regularly because research, copywriting, and design all take time and marketing skills. This workflow automates research, writing, image creation, and posting, so your channels stay active and relevant while you focus on clients and services. What This Workflow Does Generates short, engaging posts tailored to a beauty‑salon audience (hair, nails, skincare, make‑up, self‑care) using an AI agent. Uses Tavily Internet Search to pull up‑to‑date information and trends based on a reference link or topic. Turns each post into a detailed, photorealistic image prompt and creates a matching visual with an AI image model (for example, gpt‑image‑1 or other connected providers). Automatically sends the final text and image to Telegram, and can be extended to other social platforms from the Split Out node. How It Works Trigger the workflow Scheduled automatic generation:** Run the parent workflow on a schedule (for example, once per day at 9 AM) to publish new content regularly. Google Sheets trigger:** Generate content when a new row with a reference link or topic is added to your sheet. Use it when you manage ideas or briefs in Google Sheets and want the workflow to react as soon as a new idea appears. RSS Feed trigger:** Start the workflow when new items appear in a selected RSS feed. Ideal for turning fresh blog posts, news, or industry updates into social media content or automated summaries. Meta (Facebook/Instagram) webhook:** Use the Meta Reference trigger to fire the workflow on incoming webhooks from Meta (for example, new comments, messages, or events). Helpful when you want to auto‑respond, log activity, or generate follow‑up content from Meta activity. Airtable trigger:** Start the workflow when records in a selected Airtable base/table change (for example, a new idea, brief, or status update), so your posts react instantly to updates in your Airtable content board. Postgres trigger:** Fire the workflow when new rows are inserted or existing rows are updated in a connected PostgreSQL table, letting you drive content generation from events in your app database or Supabase‑style back end. Manual start:* Hit Execute workflow* whenever you want to spin up a batch of posts on demand, test new prompt settings, or debug the flow step by step. Research and generate copy The GENERATE TEXT agent calls Tavily to gather fresh information on the topic. It writes a post under 1024 characters with a hook, practical tips, relevant hashtags, and a closing line with your salon address and contact. Create the visual The GENERATE PROMPT agent converts the post into a single, clear description of the scene (client, service, salon interior, lighting, mood) with a strict “no text on image” rule. An image model such as gpt‑image‑1 or one of the HTTP image APIs renders a matching beauty visual. Distribute the content The Split Out node fans out the result so Telegram receives a photo post with the generated caption. Additional social or content nodes (for example Facebook, LinkedIn, X, template tools) can be wired after this step for multi‑channel posting. How to Customize This Workflow to Your Needs Brand voice** Edit the system message in the GENERATE TEXT node to adjust tone (luxury, friendly, clinical, playful), language, services, and city. Update the final address and phone line to match your salon details. Topics and triggers** Point the Google Sheets Trigger to your own document ID, sheet, and columns for ideas, links, or campaign themes. Use the Schedule Trigger for fully automatic posting or rely on the Manual Trigger for controlled, batch generation sessions. Models and providers** Swap GPT‑5 llm and the default image model for alternatives such as Mistral, Gemini, Anthropic, DeepSeek, or custom HTTP image APIs by enabling the corresponding nodes and adding credentials. Channels and outputs** Connect or remove social nodes after Split Out depending on which platforms you actively use. Add extra processing steps (for example resizing images or adding UTM parameters) before each channel if needed. Visual style** Tweak the GENERATE PROMPT instructions to control composition (close‑up vs. full‑body), color palette, lighting, and overall salon aesthetic, while keeping the constraint of no text or logos in the image.

Who Is This For? This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents. ​ Whether you run a blog, SaaS, personal brand, newsletter, or client accounts, this tool helps you keep a consistent content pipeline without manually writing every article, creating images, and posting to each platform one by one. ​ ​ 💪🏼 While the template is wired around classic blog + social media distribution, the underlying logic is universal. You can easily adapt it to any niche by editing prompts, swapping models, and re‑wiring nodes. You can plug in any LLM you like, from ChatGPT to Claude, Gemini, Mistral, DeepSeek, OpenRouter, or even local models through Ollama. ​ What Problem Is This Workflow Solving? 🤯 Most teams waste hours on the same repetitive loop: research a topic, gather links, write a blog post, craft social captions, generate visuals, upload everything to multiple platforms, and archive assets. ​ ​ 💎 This workflow solves that by automating the full content chain—from research and blog‑post generation to image creation, publishing across channels, and logging everything in your content database—so your feeds stay active while you focus on strategy, not busywork. ​ What This Workflow Does ✨ Generates in‑depth blog posts tailored to your topic and target audience, enriched with fresh references from the web via Tavily/SerpAPI search tools. ​ ✨ Creates an image prompt and title from the article, generates the visual with OpenAI Images (gpt-image-1), and converts it into a ready‑to‑use image file. ​ ✨ Automatically publishes content to your connected platforms (WordPress for blog posts, Telegram, X/Twitter, Facebook, LinkedIn) while saving images to Google Drive and logging each publication in Google Sheets for tracking. ​ How It Works? Surprisingly simple ☺️ The workflow is triggered by another n8n workflow or by one of several triggers (Facebook, RSS, Google Sheets, Airtable, Postgres) that pass in the blogTopic, targetAudience, and Telegram chatID. ​ ​ The Blog Post Agent (LLM with access to Tavily/SerpAPI) researches the topic, writes a structured article for the specified audience, and sends its output to the Image Prompt Agent, which turns the content into a visual prompt and title. ​ 🎯 The end result: you provide a topic, run the workflow, and receive a complete blog post, matching image, and ready‑made social posts shipped directly to your channels and archives—no manual copy‑paste. ​ How to Customize This Workflow to Your Needs 🎨 Switch AI models and fine‑tune prompts so the agent can handle your exact formats: tutorials, case studies, listicles, product updates, thought‑leadership pieces, or campaign landing posts. 🔍 Refine research sources inside Tavily/SerpAPI to prioritize the domains, blogs, and docs your audience trusts, keeping posts accurate and up to date. ⏰ Adjust posting cadence and schedules to align with peak engagement for your audience, mixing automated slots with manual “launch” runs for special announcements. 📱 Expand or trim channels as needed: keep just WordPress + LinkedIn, add Telegram as a content feed, or plug the workflow into additional automations like email campaigns or RSS feeds. 📊 Use Google Sheets as your content hub to store ideas, angles, CTAs, references, and performance notes so you can double‑down on topics and formats that perform best. 🎬 Swap images for video by replacing the image generation node with video tools (for example, Runway‑style APIs) if your strategy is video‑first while keeping the same prompt pipeline. 💾 Build a reusable prompt library in Sheets, Notion, or Airtable so you can rotate proven prompt patterns each month and keep quality high without reinventing the wheel. 🤖 The system will continuously generate blog posts, visuals, and social updates and publish them across your selected platforms while archiving everything in Drive and Sheets—keeping your brand visible, consistent, and professional with minimal ongoing effort.

Workflow Name: 💬 Demo Call Back Template was created in n8n v1.90.2 Skill Level: High Categories: n8n, Chatbot Stacks Execute Sub-workflow Trigger node Chat Trigger node Redis node Postgres node Telegram node HTTP Request node If node, Code node, Edit Fields (Set) Prerequisite Execute Sub-workflow Trigger: your own node MiniMax Account (https://www.minimax.io/) Production Features Scaling Design* for n8n Queue mode* in production environment Optional Provider Data from external Database with Caching Mechanism. Optional AI Clone Voice Message response via MiniMax API with Multi-Languages support. Optional Backup Chat Log to Database, so you can use in APP/API building. Testing Flow** with or without dependance on other workflow. Multi Chatbot** (This is a demo for Telegram, you can add WhatsApp, Line, etc) Error Management** What this workflow does? This is a n8n Telegram Output Workflow. It will receive message from other Sub-workflow then output to Telegram for Message, or Replay Message and extra Voice Message. How it works The Flow Trigger node will wait for the message from other Sub-workflow. When message is received, it will first check for the matching Provider from the PostgreSQL database. Then determine if it is a Voice message to Text message. OPTIONAL. For voice message, use the MiniMax API to generate a voice message, then send it to Telegram. Finally, send the text to Telegram. Set up instructions Pull and Set up the required SQL from our Github repository. Create you Redis credentials, refer to n8n integration documentation for more information. Select your Credentials in Provider Cache and Save Provider Cache. Create you Postgres credentials, refer to n8n integration documentation for more information. Select your Credentials in Load Member Data, Create Chat Log Input, and Create Chat Log Output. Create you Telegram credentials, refer to n8n integration documentation for more information. Select your Credentials in Telegram Voice Output, Telegram Reply Output, and Telegram Output. AI Clone Voice setup instructions (Optional) You can clone any voice with MiniMax Go to https://www.minimax.io/ and create a MiniMax account Setup the Database with the required variables found in the MiniMax TTS node That’s it How to adjust it to your needs By default, this template will use the sys_provider table provider information, you could change it for your own design. The demo use MiniMax API for AI voice cloning, you could implement any other AI your choice. The Backup Chat Log will backup all chat conversion line by line. You can use it for you own APP/API development.

Workflow Name: 🤙 Telegram Call In Template was created in n8n v1.90.2 Skill Level: High Categories: n8n, Chatbot Stacks Chat Trigger node Telegram Trigger node Redis node Postgres node Execute Sub-workflow If node, Code node, Edit Fields (Set), Extract From File Prerequisite Community nodes: n8n-nodes-google-speech Sub-workflow: Demo Call Back Sub-workflow: Demo Call Center Production Features Scaling Design* for n8n Queue mode* in production environment Optional Member Data from external Database with Caching Mechanism. Optional Voice Message to Text Message via Google STT API with Multi-Languages support. Testing Flow** with or without dependance on other workflow. Error Management** What this workflow does? This is a n8n Telegram Call In Workflow. It will wait for message from Telegram bot and sent to the Call Center to process. How it works The Telegram Trigger node will wait for the message from the Telegram bot. When message is received, it will first check for the matching Member from the PostgreSQL database. Then determine if it is a Text message or Voice message. For voice message, use the Google Speech to Text API to transcript it into text. Finally, pass the text to the next flow, i.e. the Call Center. Set up instructions n8n-nodes-google-speech Pull and Set up the required SQL from our Github repository. Go User > Settings > Community nodes, install n8n-nodes-google-speech node Follow https://www.npmjs.com/package/n8n-nodes-google-speech Setup the Google STT node Create you Telegram credentials, refer to n8n integration documentation for more information. Select your Credentials in Telegram Trigger Create you Redis credentials, refer to n8n integration documentation for more information. Select your Credentials in Member Cache and Save Member Cache. Create you Postgres credentials, refer to n8n integration documentation for more information. Select your Credentials in Load Member Data. FOR TEST ONLY. Enable the Telegram Test Output for testing from the Test Input. Remember to activate this workflow for incoming message. How to adjust it to your needs By default, this template will use the sys_member table for member information, you could change it for your own design. The demo implementation does not include failed member loading situation, you should implement based on your needs, e.g. if is_active is not true, do… You can replace the sub-workflow Demo Call Back and Demo Call Center to another flow as needs.

Who is this for? This template is for developers and automation specialists looking to create a Telegram bot that enables users to select items from a predefined list and save their choices to a Postgres database. What problem is this workflow solving? It provides a simple and efficient way to collect structured user input via Telegram and store it in a Postgres database, useful for inventory selection, order systems, or preference tracking. What this workflow does Displays a list of selectable options from a Postgres shop_list table in Telegram Saves the user’s selection back to the database Automatically deletes messages at each step to keep the chat clean Setup Create the required tables in Postgres Replace "n8n" in the provided SQL script with the appropriate schema name for your database Run the script to create the shop_list table Add necessary credentials in n8n Telegram**: Connect your Telegram bot using the Bot Token Postgres**: Add your Postgres DB credentials to allow the workflow to read/write data How to customize this workflow to your needs Modify the shop_list table to include your specific options. Adjust the Telegram messages and logic to match your use case.

Who is this for? This template is ideal for users managing Telegram channels who want to automate the process of posting messages, including text and images, directly from an bot. What problem is this workflow solving? Manually posting content to multiple Telegram channels can be time-consuming and inconsistent. This workflow automates that process, enabling efficient and consistent content delivery to one or more channels. What this workflow does This workflow connects to a Postgres database to retrieve post content and automatically sends text or image posts to designated Telegram channels where the bot is an admin. It supports scheduling and content customization through the database. Setup Create the necessary tables in your Postgres database Open the SQL script provided in the workflow. Replace "n8n" with your actual schema name. Run the script in your database to set up the required tables. Add credentials Telegram**: Create and connect a bot, ensuring it has admin access to the target channels. Postgres**: Connect your Postgres instance using valid credentials. How to customize this workflow to your needs Modify the SQL script to match your specific table or schema naming conventions. Adjust the content format or post frequency directly from your database.

Who is this for? This template is ideal for educators, HR professionals, and anyone looking to automate testing and collect responses through Telegram, while storing results in a Postgres database. What problem is this workflow solving? Manually organizing and managing tests can be time-consuming and prone to error. This workflow automates the test distribution, response collection, and scoring process, ensuring a seamless and efficient testing experience. What this workflow does Adds test content, including questions and answers, to a Postgres database Sends a Telegram bot link to test participants Automatically delivers the test via the Telegram bot Collects and stores responses Displays the participant's ranking at the end of the test Setup Create tables in Postgres Replace "n8n" in the provided SQL script with the name of your actual schema Run the script in your database to create the required tables Add credentials Set up and connect your Telegram credentials Set up and connect your Postgres credentials How to customize this workflow to your needs Modify the test content directly in the Postgres database Customize the Telegram bot messages to match your tone and branding. Adjust scoring logic if needed to reflect different evaluation methods.

How it works Any external system triggers a reminder via webhook with a tenant token — the workflow validates the token, fetches the tenant's channel config and message template from PostgreSQL, renders the message with event variables, and sends it immediately A schedule trigger runs every minute and queries events approaching their deadline window per tenant — idempotency via a reminders_sent table ensures the same reminder is never sent twice A built-in n8n form lets you register new tenants with their channel, message template and timing rules — no external backend needed Every send attempt is logged to the database with status, message sent and error details Set up steps Add your PostgreSQL credentials to all Postgres nodes (~2 min) Add your Telegram credentials to the Send Message node (~2 min) Create the required tables using the SQL schema provided in the workflow sticky note (~10 min) Register your first tenant at /form/multi-tenant-register Send events via POST /webhook/multi-tenant-webhook with x-tenant-token header

n8nClaw — Self-Hosted AI Assistant A lightweight, self-hosted AI assistant built entirely in n8n. Multi-channel messaging (Telegram, WhatsApp, Gmail), persistent memory, task management, and autonomous work — all in a single visual workflow. Inspired by OpenClaw. What It Does n8nClaw is a personal AI assistant that lives inside n8n. It connects to your messaging apps, remembers past conversations, manages tasks, and can work autonomously on your behalf. Core capabilities: Multi-channel messaging** — talk to your assistant via Telegram, WhatsApp, or Gmail Persistent memory** — conversations are summarized, embedded, and stored in a Supabase vector database for long-term recall Task management** — create, track, and complete tasks and subtasks using n8n data tables Autonomous heartbeat** — an hourly trigger lets the agent check in, process pending tasks, and act on its own Media handling** — voice messages, images, and documents sent via Telegram are processed by Gemini models Sub-agents** — delegate work to specialized agents for research, email management, document management, and tiered workers How It Works Triggers & Input Processing Four triggers feed into the agent: Telegram Trigger** — receives text, voice, images, and documents WhatsApp Webhook** — receives text messages via Evolution API Gmail Trigger** — polls for new emails every minute Hourly Heartbeat** — scheduled trigger for autonomous task processing Each trigger filters messages (e.g., by Telegram chat ID or phone number), fetches the user profile from an Init data table, and normalizes the input into a standard format (user_message, system_prompt, last_channel). Core AI Agent (n8nClaw) The central agent uses Claude Sonnet 4.5 (via OpenRouter) with a 15-message Postgres chat memory window. It receives the normalized input and decides how to respond — using tools, delegating to sub-agents, or replying directly. Tools The agent has direct access to: Task & Subtask management** — CRUD operations on n8n data tables User profile updates** — persist learned information about the user Supabase Vector Store** — RAG queries against past conversation summaries Sub-Agents Specialized agents handle domain-specific work: | Agent | Model | Purpose | |-------|-------|---------| | Research Agent | Gemini 3 Flash | Web research via Tavily + Wikipedia | | Email Manager | Claude Haiku 4.5 | Gmail operations (read, reply, send, delete, search) | | Document Manager | Claude Haiku 4.5 | Google Docs/Drive operations | | Worker 1 | Claude Haiku 4.5 | Simple tasks | | Worker 2 | Claude Sonnet 4.5 | Mid-level work | | Worker 3 | Claude Opus 4.6 | Complex reasoning | Output Routing A Switch node routes the agent's response back to the originating channel (Telegram or WhatsApp). Long-Term Memory Pipeline A separate scheduled flow runs periodically to: Pull new chat history from Postgres Aggregate and summarize conversations (Haiku 4.5) Generate embeddings (OpenAI) Store in Supabase vector database for future RAG retrieval Setup Steps Step 1: Import the Workflow Open n8n Go to Workflows → Import from File Select the n8nClaw.json file Step 2: Create Data Tables Create three n8n data tables: Init Table (user profile): | Column | Type | |--------|------| | username | string | | soul | string | | user | string | | heartbeat | string | | last_channel | string | | last_vector_id | number | Tasks Table: | Column | Type | |--------|------| | task_name | string | | task_details | string | | task_complete | boolean | | Is_recurring | boolean | Subtasks Table: | Column | Type | |--------|------| | parent_task_id | string | | subtask_name | string | | subtask_details | string | | subtask_complete | boolean | Step 3: Set Up Supabase Vector Store Create a documents table in Supabase with the pgvector extension enabled. The table should match the schema expected by n8n's Supabase Vector Store node (include a match_documents function). Step 4: Configure Credentials Set up the following credentials in n8n (only configure the channels and services you plan to use): | Credential | Required For | |-----------|-------------| | Telegram Bot API | Telegram channel | | OpenRouter API | All AI models | | Postgres | Chat memory | | Supabase | Vector store / RAG | | OpenAI API | Embeddings | | Gmail OAuth2 | Email management | | Evolution API | WhatsApp | | Google AI (Gemini) | Media processing | | Google Docs/Drive OAuth2 | Document management | | Tavily API | Web search (Research Agent) | Step 5: Update Placeholders Search the workflow for YOUR_ and replace with your actual values: | Placeholder | Replace With | |------------|-------------| | YOUR_USERNAME | Your chosen username | | YOUR_TELEGRAM_CHAT_ID | Your Telegram chat ID | | YOUR_PHONE | Your phone number (WhatsApp) | | YOUR_EVOLUTION_INSTANCE | Your Evolution API instance name | | YOUR_*_TABLE_ID | IDs of the data tables from Step 2 | | YOUR_*_CREDENTIAL_ID | Auto-populated when connecting credentials | | YOUR_PROJECT_ID | Your n8n project ID | Step 6: Activate Connect all credentials in the n8n UI Point data table nodes to your tables Update filter nodes with your Telegram chat ID / WhatsApp number Activate the workflow

This n8n template monitors your self-hosted apps for new releases across GitHub and container registries, uses Claude AI to analyze changelogs, and delivers color-coded update digests to Discord, Telegram, Slack, and ntfy. Stop finding out about updates after something breaks. Claude reads every changelog and tells you exactly what changed, what might break, and how urgent the update is — with a ready-to-run Docker update command for each release. Good to know Estimated cost is $0.01–0.03 per daily run using Claude Haiku. See Anthropic pricing for current rates. PostgreSQL logging is included but optional — the core workflow runs without a database using n8n's built-in static data for version tracking. Test mode is ON by default. Your first run pushes a sample release through the full pipeline (AI analysis, formatting, delivery) so you can verify everything works before going live. How it works Schedule trigger runs daily at 8 AM and builds a watchlist from your manually configured repos plus optional docker-compose auto-detection Checks GitHub Releases API for repos and Docker Hub/GHCR tag APIs for container images. Pre-releases and RC/beta tags are automatically filtered out Compares each release against the last known version stored in workflow static data to detect what's genuinely new Claude Haiku reads each changelog and returns a structured summary with breaking change detection, CVE/security scanning, migration steps, and urgency classification (critical/recommended/optional) Alert rules route critical and security updates to instant alerts, while everything else batches into a single daily digest sorted by urgency Formatted messages are delivered to your enabled channels with color-coded embeds, Docker update commands, and links to full release notes Release history is optionally logged to PostgreSQL for tracking update timelines How to use Add your Anthropic API key as an n8n credential, open the Configure Watcher node to set your channel URLs, and edit the Build Repo Watchlist node to add your repos — that's the minimum to get running Click "Test workflow" to push a sample release through the full pipeline and verify delivery Set test_mode to false and toggle Active — the workflow checks daily and only alerts when new releases are found Requirements Anthropic API key (setup guide) At least one delivery channel: Discord webhook (setup guide), Telegram bot, Slack app, or ntfy topic Optional: GitHub Personal Access Token for higher API rate limits (setup guide) Optional: PostgreSQL for release history logging Customizing this workflow Add or remove repos and container registries in the Build Repo Watchlist code node — pre-loaded with 10 popular self-hosted apps Enable docker-compose auto-detection to automatically build your watchlist from a compose file URL or pasted content Set per-repo alert rules including urgency overrides, instant alert flags, and channel routing Adjust the schedule, swap delivery channels, or add additional registries

This workflow prevents your AI support bot from responding to every single message by intelligently aggregating rapid-fire messages from users before generating a comprehensive response. Who's it for Support teams and bot developers who want to provide better AI responses by letting users fully explain their issue before the bot responds, reducing unnecessary back-and-forth and improving response quality. How it works When a user sends a message to your Telegram bot, the workflow: Checks if the user has an active session within the last 60 seconds If no session exists, creates a new one and starts a 60-second timer If a session is active, appends the new message to the existing conversation After 60 seconds of the first message, fetches all aggregated messages Sends the complete conversation to OpenAI for a comprehensive response Delivers the AI-generated answer back to the user via Telegram Clears the session for the next interaction Requirements Telegram bot token (set up via BotFather) OpenAI API key PostgreSQL database with a user_sessions table containing columns: user_id, session_id, messages (jsonb array), first_message_at, wait_expires_at, status, and resume_url n8n instance (self-hosted or cloud) How to set up Configure your Telegram credentials in the Telegram Trigger node Add your OpenAI API key to the OpenAI Chat Model node Set up PostgreSQL credentials and create the required database table Adjust the wait time (default 60 seconds) in the Wait node if needed Activate the workflow and test with your Telegram bot How to customize Modify the aggregation window by changing the wait duration Customize the AI prompt in the AI Agent node for different response styles Add additional logic to handle specific keywords or commands Integrate other AI models or add context from external sources

This n8n workflow automates task creation and scheduled reminders for users via a Telegram bot, ensuring timely notifications across multiple channels like email and Slack. It streamlines task management by validating inputs, storing tasks securely, and delivering reminders while updating statuses for seamless follow-up. Key Features Enables users to create tasks directly in chat via webhook integration. Triggers periodic checks for due tasks and processes them individually for accurate reminders. Routes reminders to preferred channels (Telegram, email, or Slack) based on user settings. Validates inputs, handles errors gracefully, and logs task data for persistence and auditing. Workflow Process The Webhook Entry Point node receives task creation requests from users via chat (e.g., Telegram bot), including details like user ID, task description, and channel preferences. The Input Validation node checks for required fields (e.g., user ID, task description); if validation fails, it routes to the Error Response node. The Save to Database node stores validated task data securely in a database (e.g., PostgreSQL, MongoDB, or MySQL) for persistence. The Success Response node (part of Response Handlers) returns a confirmation message to the user in JSON format. The Schedule Trigger node runs every 3 minutes to check for pending reminders (with a 5-minute buffer for every hour to avoid duplicates). The Fetch Due Tasks node queries the database for tasks due within the check window (e.g., reminders set for within 3 minutes). The Tasks Check node verifies if fetched tasks exist and are eligible for processing. The Split Items node processes each due task individually to handle them in parallel without conflicts. The Channel Router node directs reminders to the appropriate channel based on task settings (e.g., email, Slack, or Telegram). The Email Sender node sends HTML-formatted reminder emails with task details and setup instructions. The Slack Sender node delivers Slack messages using webhooks, including task formatting and user mentions. The Telegram Sender node sends Telegram messages via bot API, including task ID, bot setup, and conversation starters. The Update Task Status node marks the task as reminded in the database (e.g., updating status to "sent" with timestamp). The Workflow Complete! node finalizes the process, logging completion and preparing for the next cycle. Setup Instructions Import the workflow into n8n and configure the Webhook Entry Point with your Telegram bot's webhook URL and authentication. Set up database credentials in the Save to Database and Fetch Due Tasks nodes (e.g., connect to PostgreSQL or MongoDB). Configure channel-specific credentials: Telegram bot token for Telegram Sender, email SMTP for Email Sender, and Slack webhook for Slack Sender. Adjust the Schedule Trigger interval (e.g., every 3 minutes) and add any custom due-time logic in Fetch Due Tasks. Test the workflow by sending a sample task creation request via the webhook and simulating due tasks to verify reminders and status updates. Monitor executions in n8n dashboard and tweak validation rules or response formats as needed for your use case. Prerequisites Telegram bot setup with webhook integration for task creation and messaging. Database service (e.g., PostgreSQL, MongoDB, or MySQL) for task storage and querying. Email service (e.g., SMTP provider) and Slack workspace for multi-channel reminders. n8n instance with webhook and scheduling enabled. Basic API knowledge for bot configuration and channel routing. Modification Options Customize the Input Validation node to add fields like priority levels or recurring task flags. Extend the Channel Router to include additional channels (e.g., Microsoft Teams or SMS via Twilio). Modify the Schedule Trigger to use dynamic intervals based on task urgency or user preferences. Enhance the Update Task Status node to trigger follow-up actions, like archiving completed tasks. Adjust the Telegram Sender node for richer interactions, such as inline keyboards for task rescheduling. Explore More AI Workflows: Get in touch with us for custom n8n automation!

🔐 Human-in-the-Loop Approval Flow (n8n + Postgres + Telegram) 👥 Who’s it for Teams that need a manager approval step before a ticket or request can change status. Great for internal ops, IT requests, or any workflow where “a human must sign off.” ⚡ What it does 📨 Manager receives approval/reject link 🔑 Link is signed with HMAC + expiry (secure & tamper-proof) 🗄️ Postgres updates the ticket status 📝 Audit trail records every decision 📲 Telegram notifies both manager and requester ⏰ Expired or invalid links trigger alerts and logs 🛠 Requirements n8n instance (self-hosted) Postgres database (with tickets, ticket_audit, workflow_errors) Telegram bot token One environment variable set: SECRET_KEY ⚙️ How to set up Set SECRET_KEY in .env Create Postgres tables (SQL provided) Add Telegram + Postgres credentials in n8n Import the workflow JSON Test by opening an approval/reject link in your browser 🎨 How to customize Change who the “manager” is (currently hardcoded in the Code node). Swap Telegram for Slack or email notifications. Extend the audit schema to include more metadata (IP, username).

Telegram ticket intake and status tracking with Postgres Who’s it for Anyone running support requests through Telegram, Email, Webhooks, and so on who needs a lightweight ticketing system without paying Zendesk prices. Ideal for small teams, freelancers, or businesses that want tickets logged in a structured database (Postgres) and tracked automatically. I'm using Telegram since it's the most convenient one. How it works / What it does This workflow turns (Telegram) into a support desk: Receives new requests via a Telegram bot command. Creates a ticket in a Postgres database with a correlation ID, requester details, and status. Auto-confirms back to the requester with the ticket ID. Provides ticket updates (status changes, resolutions) when queried. Keeps data clean using dedupe keys and controlled input handling. How to set up Create a Telegram bot using @BotFather and grab the token. Connect your Postgres database to n8n and create a tickets table: CREATE TABLE tickets ( id BIGSERIAL PRIMARY KEY, correlation_id UUID, source TEXT, external_id TEXT, requester_name TEXT, requester_email TEXT, requester_phone TEXT, subject TEXT, description TEXT, status TEXT, priority TEXT, dedupe_key TEXT, chat_id TEXT, created_at TIMESTAMP DEFAULT NOW(), updated_at TIMESTAMP DEFAULT NOW() ); Add your Telegram and Postgres credentials in n8n (via the Credentials tab, not hardcoded). Import the workflow JSON and replace the placeholder credentials with yours. Test by sending /new in Telegram and follow the prompts. Requirements n8n (latest version recommended) Telegram bot token Postgres instance (local, Docker, or cloud) How to customize the workflow Change database fields if you need more requester info. Tweak the Switch node and Comands for multiple status types. Extend with Slack, Discord, or email nodes for broader notifications. Integrate with external systems (CRM, project management) by adding more branches.

How it works This workflow automatically pulls daily signup stats from your PostgreSQL database and shares them with your team across multiple channels. Every morning, it counts the number of new signups in the last 24 hours, formats the results into a concise report, and posts it to Slack, Microsoft Teams, and Telegram. This ensures your entire team stays updated on customer growth without manual queries or reporting. Step-by-step Daily Trigger & Data Fetching The Daily Report Trigger runs at 9:00 AM each day. The Fetch Signup Count node queries the customers table in PostgreSQL. It calculates the number of new signups in the last 24 hours using the created_at timestamp column. Report Preparation The Prepare Report Message node formats the results into a structured message: Report date Signup count A clear summary line: Daily Signup Report – New signups in the last 24h: X Multi-Channel Delivery The prepared message is sent to multiple platforms simultaneously: Slack Microsoft Teams Telegram This ensures all teams receive the update in their preferred communication tool. Why use this? Automates daily customer growth reporting. Eliminates manual SQL queries and report sharing. Keeps the whole team aligned with real-time growth metrics. Delivers updates across Slack, Teams, and Telegram at once. Provides simple, consistent reporting every day.

📈 AI Stock Analytics & BCS "Profit" Social Network Publishing Workflow This workflow automatically generates stock market insights for selected tickers (e.g. GAZP, SBER, LKOH) using historical data, technical indicators, and an AI model. The results are then sent to Telegram for quick moderation and publishing. 🔑 What this workflow does Runs twice a day** on a schedule with a predefined list of tickers. Fetches historical market data** from a broker API. Calculates key technical indicators** (RSI, EMA/SMA, MACD, Bollinger Bands, ADX). Generates an investment post** (title + summary) using an LLM. Stores results** in a PostgreSQL database. Sends a draft post to Telegram* with inline buttons *“Publish” and “Retry”. Handles Telegram actions**: publishes the post to the final channel or re-runs the generation process. 📌 Key features Multi-ticker support in a single run. Automatic error handling (e.g. missing data or invalid AI JSON output). Human-in-the-loop moderation through Telegram before publishing. PostgreSQL integration for history and analytics storage. Flexible structure: easy to extend with new tickers, indicators, or publishing channels. 🛠️ Nodes used Trigger:** Schedule (twice daily) + Telegram Trigger (button callbacks). Data:** HTTP Request (broker API), Function (technical analysis calculations). AI:** OpenAI / OpenRouter with structured JSON output. Storage:** PostgreSQL (analytics history). Messaging:** Telegram (drafts and publishing). 🚀 Who is this for Fintech startups looking to automate market content. Investment bloggers posting daily stock analysis. Analysts experimenting with trading strategies on real market data.

GiggleGPTBot — Witty Telegram Bot with AI & Postgres 📝 Overview GiggleGPTBot is a witty Telegram bot built with n8n, OpenRouter, and Postgres. It delivers short jokes, motivational one-liners, and playful roasts, responds to mentions, and posts scheduled witty content. The workflow also tracks user activity and provides lightweight statistics and leaderboards. ✨ Features 🤖 AI-powered humor engine — replies with jokes, motivation, random witty lines, or sarcastic roasts. 💬 Command support — /joke, /inspire, /random, /roast, /help, /stats, /top. 🎯 Mention detection — replies when users tag @GiggleGPTBot. ⏰ Scheduled posts — morning jokes, daily motivation, and random wisdom at configured times. 📊 User analytics — counts messages, commands, reactions, and generates leaderboards. 🗄️ Postgres persistence — robust schema with tables for messages, responses, stats, and schedules. 🛠️ How It Works Triggers Telegram Trigger — receives all messages and commands from a chat. Schedule Trigger — runs hourly to check for planned posts. Processing Switch routes commands (/joke, /inspire, /random, /roast, /help, /stats, /top). Chat history fetches the latest context. Mention Analysis determines if the bot was mentioned. Generating an information response builds replies for /help, /stats, /top. AI nodes (AI response to command, AI response to mention, AI post generation) craft witty content via OpenRouter. Persistence Init Database ensures tables exist (user_messages, bot_responses, bot_commands, message_reactions, scheduled_posts, user_stats). Logging nodes update stats and store every bot/user interaction. Delivery Replies are sent back via Telegram Send nodes (Send AI response, Send info reply, Reply to Mention, Submit scheduled post). ⚙️ Setup Instructions Create a Telegram Bot with @BotFather and get your API token. Add credentials in n8n: Telegram API (your bot token) OpenRouter (API key from openrouter.ai) Postgres (use your DB, Supabase works well). Run the Init Database node once to create all required tables. (Optional) Seed schedule with the Adding a schedule node — it inserts: Morning joke at 06:00 Daily motivation at 09:00 Random wisdom at 17:00 (Adjust chat_id to your group/channel ID.) Activate workflow and connect Telegram Webhook or Polling. 📊 Database Schema user\_messages** — stores user chat messages. bot\_responses** — saves bot replies. bot\_commands** — logs command usage. message\_reactions** — tracks reactions. scheduled\_posts** — holds scheduled jokes/wisdom/motivation. user\_stats** — aggregates per-user message/command counts and activity. 🔑 Example Commands /joke → witty one-liner with light irony. /inspire → short motivational phrase. /random → unexpected witty remark. /roast → sarcastic roast (no offensive targeting). /stats → shows your personal stats. /top → displays leaderboard. /help → lists available commands. @GiggleGPTBot + message → bot replies in context. 🚀 Customization Ideas Add new command categories (/quote, /fact, /news). Expand analytics with reaction counts or streaks. Localize prompts into multiple languages. Adjust CRON schedules for posts. ✅ Requirements Telegram Bot token OpenRouter API key Postgres database 📦 Import this workflow, configure credentials, run the DB initializer — and your witty AI-powered Telegram companion is ready!

✉️ AI-Powered 3-Step B2B Pipeline — Lead Gen → Cold Outreach → AI Drafted Email Management Automate your outbound workflow from prospecting to AI-generated reply drafts in Gmail — all fully integrated with your database. Ideal for SDRs, founders, and growth agencies who want speed, personalization, and control without losing human review. 📌 Example: From a verified lead list to a qualified opportunity — fully tracked, classified, and pre-drafted with this automation. 🚀 What This Workflow Does Step 1 — Lead Generation Import leads from Apollo. Enrich and verify emails. Store results in Supabase/Postgres, Step 2 — Cold Outreach Send 3 step personalized sequences via Mailgun/SendGrid. Track delivery, opens, replies, and bounces directly in your DB. Step 3 — Email Management (AI Drafts) Process only incoming Gmail messages from contacts in your DB. Generate personalized reply drafts, label threads, update lead status, and alert your team via Slack/Telegram. 🔗 Integrated Services Database:** Supabase/Postgres Outbound Email:** Mailgun / SendGrid Inbound Email & Drafts:** Gmail (OAuth2) AI Models:** OpenAI / Anthropic (JSON mode for classification + drafting) Alerts:** Slack / Telegram (optional) 💼 What You Get Detailed setup guide Fully connected 3-step pipeline in n8n Ready-to-use database schema Pre-built AI prompts for intent classification and professional replies 📥 Perfect For SDR teams doing targeted outbound Agencies managing multiple client campaigns Founders building scalable outbound systems Sales ops needing a no-risk, review-first reply process 💡 Why You’ll Love It This isn’t just another outreach template — it’s a full sales engine. From verified leads to AI-drafted replies, every action is logged, tracked, and controlled for maximum conversions without sacrificing oversight.

Filter incoming emails via IMAP, extract & clean the body into plain text, normalize (title/slug/snippet/date/from/url), check for duplicates in Postgres, store as a row in a Notion database, then send a Telegram notification. Perfect for building a knowledge base or inbox triage automation without duplicate noise. Key Features IMAP polling (Only UNSEEN). Extract & clean HTML → plain text. Normalization: title, snippet, bodyText, slug, messageId, sentAt, fromAddress, sourceUrl. Deduplication via Postgres (SELECT EXISTS). Create page in Notion database (property mapping). Telegram success notification. Tags: email, imap, notion, postgres, deduplication, telegram, automation, knowledge-base Prerequisites IMAP access (Gmail/Outlook/Custom). Gmail: enable IMAP + App Password if using 2FA. Notion Integration Token & Database ID (database must be shared with the integration). PostgreSQL accessible from n8n. (Optional) Telegram Bot Token & Chat ID.

This workflow automates the process of monitoring Twitter accounts for intelligence gathering. It fetches new tweets from specified accounts via RSS, uses a powerful AI model (Google Gemini) to analyze the content based on your custom prompts, and sends formatted alerts to a Telegram chat for high-priority findings. Key Features: Scheduled Execution: Runs automatically at your desired interval. Dynamic Configuration: Manage which Twitter accounts to follow and what AI prompts to use directly from a Postgres database. AI-Powered Analysis: Leverages Google Gemini to extract summaries, keywords, and assign an importance level to each tweet. Duplicate Prevention: Keeps track of the last processed tweet to ensure you only get new updates. Customizable Alerts: Sends well-structured and easy-to-read notifications to Telegram. Setup Required: Postgres Database: Set up a table to store your configuration (see the Sticky Note in the workflow for the required schema). RSSHub: You need access to an RSSHub instance to convert Twitter user timelines into RSS feeds. Credentials: Add your credentials for Postgres, Google AI (Gemini), and your Telegram Bot in n8n. Configuration: Update the placeholder values in the RSS and Telegram nodes (e.g., your RSSHub URL, your Telegram Chat ID).

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. AI-Powered Cold Email Sequence Workflow for n8n Unlock advanced cold email automation and boost your outbound results with this robust n8n workflow, engineered for scale, personalization, and flexibility. Harness AI-driven email content, dynamic lead handling, and intelligent scheduling—without writing code. What’s Inside Intelligent Multi-Step Email Outreach Automate 3-step cold email sequences for every prospect—all fully personalized and contextually adapted through AI research and copy generation. Each contact receives tailored, timely emails designed to maximize engagement and reply rates. Automated Personalization at Scale For every new lead, the workflow: Researches company and role context** using AI Identifies key pain points** and crafts custom hooks Builds multi-language, well-formatted HTML emails** with a consistent, brand-aligned tone This produces authentic, individualized communication—far more effective than generic mail merges. Advanced Scheduling & Delivery Logic Smart scheduling**: Sends distributed across optimal days/hours (configurable for your market) Throttled delivery**: Drip batching and dynamic waits to preserve deliverability Automated follow-ups**: Gentle, contextual nudges at precise intervals if there’s no reply Lead Management & Expansion Seamless database integration**: Email history, logic, and lead data fully synchronized with your backend (Supabase support included) Integrated lead generation**: Suite includes a companion workflow for sourcing, deduplicating, and enriching leads using Apollo, GPT-4, and AI—feeds directly into your campaign pipeline Built for Reliability and Scale Resilient against errors and duplicate sends Multi-sender rotation** for reputation management Easily customizable scheduling, content, languages, and batch size Tracks all critical data fields, like send history and reply status Use Cases B2B Sales Development** Automated Candidate Outreach (Recruitment)** Newsletter or Event Drip Campaigns** Startup Go-to-Market Sequences** Agency Lead Generation** Template Highlights AI-Powered Personalization**: Cold emails crafted by GPT-4 and prompt engineering Omnichannel Scheduling**: Dynamic batching, throttling, sender rotation Works Out-of-the-Box**: Connects to Mailgun, OpenAI, Supabase—simply insert credentials and leads Companion Lead Gen Workflow: Includes Apollo–AI–database pipeline for continuous sourcing that you can acces **for free in my profile. Flexible & Modular**: Adapt language, schedule, templates, or trigger events as your strategy evolves Best Practice Features No PII or sensitive data embedded—safe for corporate teams Modular zones for sequence creation, delivery, and tracking—clarity and easy expansion Clearly-named nodes and logical flows, following n8n community standards Robust error handling for high deliverability and low maintenance Experience end-to-end intelligent email automation—powered by n8n, trusted integrations, and state-of-the-art AI. Both the cold outreach workflow and the lead generation template are included. Discover, engage, and convert—at scale.

My Telegram bot provides specialized support through dedicated slash commands for different departments. Users can directly access the right support team using: /billing - For payment and invoice questions /tech-support - For technical assistance /return-policy - For returns and refunds Key Features: Command-based routing Direct department access via slash commands State management Tracks active conversations in PostgreSQL Knowledge base integration Pinecone vector stores for each department Auto-updating New Google Drive documents automatically populate the knowledge base Context-aware Maintains department choice

Who is this for? This workflow is for Telegram bot developers or marketers who want to verify user subscriptions to specific Telegram channels and optionally reward them with downloadable files. What problem is this workflow solving? This workflow ensures users have subscribed to required Telegram channels before they are granted access to resources or rewards, such as Google Drive files. It automates the subscription verification process, saving time and reducing manual effort. What this workflow does Verifies if a user is subscribed to specific Telegram channels. Allows adding and removing channel IDs for verification. Sends referral links to users for subscription checks. Optionally grants access to Google Drive files upon successful verification (currently inactive) Setup Add the bot to your Telegram channels as an admin – this is required for the bot to check subscription status. Add channel IDs via the bot – these are the channels users will need to subscribe to. Send the referral link to users you want to verify. Remove channels anytime from the subscription check list if needed. Create tables in Postgres: Replace "n8n" in the provided SQL script with your DB schema name. Run the script in your Postgres DB. Add credentials: Telegram Postgres How to customize this workflow to your needs Modify the SQL script to suit your existing database structure. Adjust the logic to enable or disable file delivery from Google Drive.

Who is this for? This workflow is ideal for businesses or individuals who want to run Telegram-based giveaways that require users to subscribe to certain channels in order to participate. What problem is this workflow solving? Running a fair and trackable giveaway on Telegram can be difficult without a system that verifies subscriptions and manages participants. This workflow simplifies that process, ensuring only eligible users are included and enabling a smooth drawing process. What this workflow does The giveaway organizer specifies a list of Telegram channels for participants to must subscribe to. The organizer shares a bot link with users. Users start the bot, confirming their participation in the giveaway. The bot tracks eligible participants. The administrator complete the giveaway and select winners. Setup Create tables in your Postgres database Open the provided SQL script. Replace "n8n" with your schema name. Execute the script in your Postgres DB. Add credentials in n8n Telegram credentials (Bot token, etc.) Postgres database credentials How to customize this workflow to your needs Modify the SQL script to match your database schema if needed. Customize the Telegram bot messages and logic using the n8n Telegram nodes. Add additional nodes if you want to notify winners or log data in other services.