How I Built an AI Telegram Bot That Runs 24/7
Provides creators with an accessible entry point into continuous cloud-hosted agent deployment, expanding automation beyond local system constraints.
What this lesson covers
This video details how to build and host an automated AI Telegram bot using BotFather and the open-source Hermes agent framework deployed on a Hostinger cloud server. It demonstrates setting up persistent memory, live web scraping, and transforming repetitive user commands into reusable skills.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:25 ↗
Register a custom Telegram bot with BotFather using the `/newbot` command to obtain an API access token.
- 1:27 ↗
Retrieve your unique user ID with the userinfobot to restrict bot execution rights exclusively to your account.
- 2:38 ↗
Deploy the Hermes agent on a Hostinger VPS cloud server to ensure 24/7 continuous uptime after shutting down your local machine.
- 4:39 ↗
Execute `Hermes setup` in the server terminal to link your Telegram API key, allowed user ID, and AI model credits.
- 6:32 ↗
Prompt the Hermes agent directly within Telegram to turn multi-step tasks into permanent, reusable skills.
Workflow outlined in the video
- Create a Telegram bot via BotFather and copy the secret API token.
- Obtain your Telegram user ID using userinfobot for authentication control.
- Set up a Hostinger VPS cloud server instance configured for Hermes deployment.
- Open the server terminal and run `Hermes setup` in full setup mode.
- Input the Telegram token, allowed user ID, AI credits, and enable Oxyabs web search skills.
- Send task instructions to the bot in Telegram and instruct it to save the process as a named skill.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
How to interpret the numbers
22,097 views captured 27 September 2026. ReelStack recommendation score: 28/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.54× views vs 6 other channel videos observed at a similar age. View-evidence factor 96% (views / (views + 1,000))
- 25% freshness: 21/100 with a 14-day half-life
- 20% momentum: 234 views/day vs 426 channel baseline (3 comparable uploads), with the same view-evidence factor
- 10% engagement: 5/100; likes + 4× comments, smoothed with a 500-view neutral prior