Self-learning AI assistant with permanent memory | GPT,Telegram & Pinecone RAG
Your AI secretary that self-learning every day and remembers everything you said (text, audio, image). Imagine having a personal AI secretary accessible right from your Telegram, ready to assist you with information and remember everything you discuss. This n8n workflow transforms Telegram into your intelligent assistant, capable of understanding text, audio, and images, and continuously learning from your interactions. It integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. It builds and queries a powerful vector database in real-time, ensuring relevant and accurate responses. Video guidance on how to set up Telegram integration is also included. Who is this for? This template is ideal for: Individuals seeking a personal AI assistant for quick information retrieval and note-taking. Professionals who need to keep track of important conversations and insights. Anyone interested in leveraging the power of Retrieval-Augmented Generation (RAG) and vector databases for personal knowledge management. Users who want a self-learning AI that improves over time based on their interactions. What problem is this workflow solving? This workflow integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. This workflow addresses the challenge of information overload and the need for an easily accessible, personalized knowledge base. It eliminates the need to manually organize notes and search through past conversations. By automatically storing and retrieving information from a vector database, this workflow makes it effortless to access the knowledge you need, when you need it. It also provides a way to retain information from various media types like voice notes and images. What this workflow does: This workflow automates the following steps: Instant Information Capture: Receives text messages, audio notes (transcribed), and images (with content analysis) directly from your Telegram. Intelligent Question Answering: When you ask a question, the AI searches its knowledge base (Pinecone vector store) for relevant information and provides a comprehensive answer. It even considers your recent conversations for context. Automatic Knowledge Storage: When you make a statement or provide information, the AI extracts key details and saves them in a Google Docs "memory palace." Daily Self-Learning: Every day, the workflow automatically takes all the information stored in the Google Docs, converts it into a vector representation, and adds it to its knowledge base (Pinecone vector store). This ensures the AI continuously learns and remembers everything you've shared. Image Understanding: Extracts text and information from images you send. Audio Transcription: Automatically transcribes your voice notes into text for processing and storage. Short-Term Memory: Remembers recent interactions within a session for more context-aware conversations. Setup: To get started, you'll need to connect the following services to your n8n instance: Telegram: Connect your Telegram bot API credentials. A video guidance is included for telegram integration setup. OpenAI: Provide your OpenAI API key for audio transcription and image analysis. Pinecone: Set up a Pinecone account and provide your API key and environment. Create a namespace in Pinecone. Google Docs: Connect your Google account with access to Google Docs. You'll need to create a Google Doc that will serve as the daily "memory palace" and provide its ID in the workflow. How to customize this workflow: Adjust the AI Agent's Personality: Modify the system prompt in the "AI Agent" node to tailor the AI's tone and behavior. Expand Knowledge Sources: Integrate other data sources into the daily learning process, such as emails or other documents, by adding more nodes to the scheduled trigger workflow. Add More Tools for the AI Agent: Integrate additional tools into the AI Agent, such as web search or other APIs, to further enhance its capabilities. Modify the Daily Schedule: Adjust the schedule trigger to run at a different time or interval.
By TianyiSync tasks automatically from Todoist to Notion
This workflow checks if the task in Todoist has a specific label and based on that creates a new database page in Notion. Prerequisites Todoist account and Todoist credentials Notion account and Notion credentials How it works To start the workflow add a task to Todoist and mark it with a label, e.g. “send-to-n8n”. Wait a maximum of 30 seconds. Todoist node identifies the tasks marked as “send-to-n8n”. Notion node creates a new Notion database page. Notice Notion has a new task now with the same name as in Todoist.
By n8n TeamGmail to Slack: AI-scored Upwork job alerts with OpenRouter
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Overview When applying for freelance jobs on Upwork, minutes matter. The first quality application is more often than not the one that's ultimately selected. Subscribers to Upwork's Freelancer Plus receive email job alerts, but filters are very limited. As a result, it takes a lot of time to manually go through each email and determine if each job fits your criteria. This workflow scans your Gmail every few minutes, finds all Upwork job alerts, scores them based on your profile/preferences, and sends a Slack channel message for jobs that are strong potential matches. How it works Scans Gmail for Upwork job alerts every few minutes Extracts all available job data from each email Scores the job based on profile information and criteria you provide Sends a Slack notification for all jobs that meet a given score threshold Disclaimers This workflow polls Gmail for new messages every 10 minutes. A workflow execution will be used each time, regardless of whether the Gmail scan finds anything. You may want to adjust this frequency based on the amount of workflow executions you want to use. The AI matching process is based only on the information included in the email body (job title, description snippet and metadata). It is against Upwork's Terms of Service to scrape a full job posting. Despite this, the quality of the results in our testing is high for most use cases. Required Setup Subscribe to Upwork's Freelancer Plus plan to enable job alerts ($19.99/mo at the time of this posting) Create Gmail and Open Router (or an LLM provider of your choice) credentials and select them in the Gmail / LLM Model nodes Create a Slack app that has at least the chat:write.public and channels:read scopes, install it into your workspace, and use your apps OAuth Token to create a Slack API credential in n8n IMPORTANT: In the "Opportuntity Scorer" node, replace the text in between the <my_profile> tags with your freelancer bio. For best results, include as much detail as possible about your skillset, experience, tool familiarity, and job preferences. Update the filter with your notification threshold preference(s) and update the Slack channel to send notifications to in the last Slack node If you have any questions or feedback about this workflow, or would like me to build custom workflows for your business, email me at n8n@paperjam.agency.
By James FrancisSending an SMS with MessageBird
No description available.
By tanaypantGenerate domain insights with WHOIS lookup and GPT-5-Nano via RapidAPI
This template allows you to automatically fetch WHOIS data for any domain and display it in a clean, modern HTML card. It doesn’t just stop at showing raw registry data — it also uses a lightweight AI model to generate a short analysis or conclusion about the domain. It’s designed for SEO specialists, web developers, sysadmins, digital marketers, and cybersecurity enthusiasts who want quick and structured access to domain ownership and status details without wasting time on manual searches. What it does: Receives a domain name via webhook. Queries the WHOIS API through RapidAPI. Extracts and formats key details (registrar, creation date, expiry date, DNS, domain status, etc.). Uses AI (GPT-5-Nano) to generate a short descriptive insight about the domain. Returns everything in a responsive, styled HTML card (light + dark mode included). Requirements: A free account on RapidAPI.com. Use of the Bulk WHOIS API (includes up to 1,000 requests per month free, no credit card required). Who is it for? SEO professionals who need to quickly check domain lifespans, expirations, and registrar info. Web developers who want to integrate WHOIS checks into dashboards, apps, or chatbots. IT admins & security teams who monitor domains for fraud, abuse, or expiry. Entrepreneurs & marketers researching competitors’ domains. This template saves time, improves workflows, and makes WHOIS data both actionable and user-friendly.
By Oriol SeguíeBay analytics API rate limit monitoring for AI agents
Complete MCP server exposing 2 Analytics API operations to AI agents. ⚡ Quick Setup Need help? Want access to more workflows and even live Q&A sessions with a top verified n8n creator.. All 100% free? Join the community Import this workflow into your n8n instance Credentials Add Analytics API credentials Activate the workflow to start your MCP server Copy the webhook URL from the MCP trigger node Connect AI agents using the MCP URL 🔧 How it Works This workflow converts the Analytics API into an MCP-compatible interface for AI agents. • MCP Trigger: Serves as your server endpoint for AI agent requests • HTTP Request Nodes: Handle API calls to https://api.ebay.com{basePath} • AI Expressions: Automatically populate parameters via $fromAI() placeholders • Native Integration: Returns responses directly to the AI agent 📋 Available Operations (2 total) 🔧 Rate_Limit (1 endpoints) • GET /rate_limit/: Retrieve Application Rate Limits 🔧 UserRateLimit (1 endpoints) • GET /userratelimit/: Retrieve User Rate Limits 🤖 AI Integration Parameter Handling: AI agents automatically provide values for: • Path parameters and identifiers • Query parameters and filters • Request body data • Headers and authentication Response Format: Native Analytics API responses with full data structure Error Handling: Built-in n8n HTTP request error management 💡 Usage Examples Connect this MCP server to any AI agent or workflow: • Claude Desktop: Add MCP server URL to configuration • Cursor: Add MCP server SSE URL to configuration • Custom AI Apps: Use MCP URL as tool endpoint • API Integration: Direct HTTP calls to MCP endpoints ✨ Benefits • Zero Setup: No parameter mapping or configuration needed • AI-Ready: Built-in $fromAI() expressions for all parameters • Production Ready: Native n8n HTTP request handling and logging • Extensible: Easily modify or add custom logic > 🆓 Free for community use! Ready to deploy in under 2 minutes.
By David AshbyMonitor and report OKR variance from Monday.com and Jira via Slack and Email
Description Synchronize OKRs (Objectives and Key Results) between Monday.com and Jira to automatically calculate progress variance, update dashboards, and share variance reports via Slack and Outlook. This workflow ensures teams have accurate, real-time visibility into performance metrics and project alignment — without manual reconciliation. 🎯📈💬 What This Template Does Step 1: Triggers daily at a scheduled time to fetch the latest OKRs from Monday.com. ⏰ Step 2: Extracts Key Results and their linked Jira epic keys from the OKR board. 🔗 Step 3: Fetches corresponding Jira epic details such as status, assignee, and last updated date. 🧩 Step 4: Merges Monday.com KR data with Jira epic progress through SQL-style joins. 📋 Step 5: Calculates real-time progress and variance against target goals. 📊 Step 6: Updates Monday.com KR items with actual progress, variance percentage, and status (“On Track”, “At Risk”, or “Ahead”). 🔄 Step 7: Aggregates all KR data into a consolidated report for communication. 📦 Step 8: Sends formatted variance reports to Slack and Outlook, with summaries of owner, progress, and variance metrics. 📢 Key Benefits ✅ Automates end-to-end OKR and Jira synchronization ✅ Eliminates manual progress tracking errors ✅ Provides daily visibility on team and project health ✅ Enables proactive risk detection via variance thresholds ✅ Keeps all stakeholders updated via Slack and Outlook ✅ Centralizes OKR performance metrics for reporting Features Daily scheduled trigger for automatic OKR sync Monday.com → Jira data integration via API Real-time variance computation logic Automatic updates of OKR fields in Monday.com SQL-style data merging and aggregation Slack notification with variance summaries Outlook email digest with formatted HTML tables Requirements Monday.com API credentials with board access Jira API credentials with permission to view epics Slack Bot token with chat:write permissions Microsoft Outlook OAuth2 credentials for sending emails Environment variables for board, channel, and recipient configuration Target Audience Product and engineering teams managing OKRs across platforms 🎯 Project managers tracking cross-tool performance metrics 📋 Leadership teams needing automated OKR reporting 💼 Operations and strategy teams monitoring execution health 🧭 Step-by-Step Setup Instructions Connect your Monday.com, Jira, Slack, and Outlook credentials in n8n. 🔑 Replace MONDAYBOARDID, GROUP_ID, and column identifiers with your own. 🧩 Set environment variables for SLACKCHANNELID and REPORTRECIPIENTEMAIL. 💬 Adjust the cron expression to define your sync frequency (e.g., daily at 9 AM). ⏰ Test the workflow with a single OKR item to confirm successful synchronization. 🧠 Enable the workflow to automate daily OKR variance tracking and reporting. ✅
By Rahul Joshi