Gregory
Backend & ML engineer with passion for automation and MVP building. Co-founder of lemon-ai.com, AI engineer at DarwinApps, creator of https://studyjunkie.co
Templates by Gregory
Publish LinkedIn & X posts with Telegram Bot, Gemini AI & Vector Memory
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Overview This is a Telegram Bot capable of receiving information from the user in the form of text messages, voice messages, images or documents (e.g., presentations, PDFs, HTML pages), and publishing posts to the user's social platforms. The bot always sends the user a draft of the post for verification before publishing it. The bot saves relevant information to its long-term memory (vector store), so you don't need to repeat it in every interaction (e.g., who you are, your company, product, etc.). This template supports creating posts in LinkedIn and X. Setup Requirements To use this template your will need: Google's AI Studio API key. Get one here: https://aistudio.google.com/app/apikey Telegram Bot API key. You receive one when you register a new Telegram Bot via @BotFather bot in Telegram. LinkedIn API key. Follow the instructions here to create one: https://docs.n8n.io/integrations/builtin/credentials/linkedin/ X API key. Follow the instructions here to create one: https://docs.n8n.io/integrations/builtin/credentials/twitter/ Step-by-step instruction Import this template Create a new Telegram Bot or get an API key for existing one. Configre Telegram nodes with Telegram API key. Obtain a Google's AI Studio API key. Set it in "Describe document", "Describe audio" and "Google Gemini Chat Model". Create an API key for LinkedIn. Create an API key for X. Set our LinkedIn key in "Create post in LinkedIn" nodes. Set your X key in "Create X (Twitter) post" node. Other Bright-colored notes in the template highlight information that needs to be set before launching the template.
By GregoryForward email & LinkedIn message notifications from Reply.io to Telegram
How this works: This workflow contains a webhook that receives updates from Reply.io when one of your connections sends you a message via either Email or LinkedIn. The workflow also includes utility nodes to create the necessary webhook subscriptions. Setup steps: Configure the body of the utility nodes to create subscriptions for the correct URL — retrieve it from the "Webhook" node in the workflow (use the production URL) Obtain your Reply.io API key. Documentation: https://apidocs.reply.io/ Create a Telegram bot Set your Reply.io API key in the HTTP nodes using Header Authentication Enter your Telegram credentials in the Telegram node Activate the workflow
By GregoryBatch process data with Redis-powered debouncing system
How it works This implementation aggregates incoming data into a Redis list from potentially concurrent workflow executions. It buffers the data for a set period before a single execution retrieves and processes the entire batch. Step-by-step Flow: Trigger: Data is received from a trigger (e.g., an external workflow execution). Lock Check: The system verifies that the queue is not currently locked; if it is, the process waits. Append: The received data is appended to a Redis list. Tagging: A unique execution identifier is generated and written to a specific Redis key (acting as a "last writer" marker). Wait: The execution pauses for a configured duration. Verification: After the wait, the execution checks if the Redis key still contains its specific identifier. Exit Condition: If the identifier has changed, it indicates a newer execution has arrived. The current execution terminates. Processing: If the identifier matches, this execution assumes responsibility for the batch. It locks the queue, retrieves all data, clears the Redis list, releases the lock, and forwards the aggregated data further. Setup Add your Redis instance credentials Configure the debounce period (2 seconds by default) Adjust this workflow's trigger and what it calls in the end
By Gregory