Hacker News Trends to Telegram
Every four hours, fetches Hacker News via Algolia, scores trends by velocity, and sends a clean HTML digest to Telegram.
What it does
You receive a clean HTML digest of trending Hacker News stories on your Telegram every four hours. The system automatically scores trends by velocity, filters out low-engagement posts, and optionally translates summaries before delivering the results to you.
Step by step
- Configure the HTTP Request node to call Algolia's Hacker News search endpoint with a query for recent posts.
- Implement the popularity velocity calculation in the Code node using post score, comment count, and time since publication.
- Format the final digest content into valid HTML string structure before passing it to the Telegram API.
Where the LLM does the work
- Generate concise, engaging summaries for each filtered post to improve readability in the Telegram channel.
- Translate summaries into other languages if the user has enabled multi-language support in the configuration.
- Refine the tone of the digest introduction to match a specific style like professional or casual.
Watch out for
Telegram message length exceeds 4096 characters easily with multiple posts, so split long digests into separate messages.
OpenRouter model latency may delay the digest delivery, consider caching summaries or using a faster model endpoint.
HTML tags in post titles can break the Telegram formatting, strip all HTML entities before sending to the API.
Tools that fit
HTTP Request API Fetch data from Algolia API
Code Service Calculate Gravity Score and filter noise
AI Agent LLM Translate titles and summaries
OpenRouter Chat Model Service Provide LLM capabilities for translation
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Hacker News Trends to Telegram: Every four hours, fetches Hacker News via Algolia, scores trends by velocity, and sends a clean HTML digest to Telegram. ## Specification - What it does: You receive a clean HTML digest of trending Hacker News stories on your Telegram every four hours. The system automatically scores trends by velocity, filters out low-engagement posts, and optionally translates summaries before delivering the results to you. - Trigger: On a schedule (Scheduled · every 4 hours) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - HTTP Request: Fetch data from Algolia API - Code: Calculate Gravity Score and filter noise - AI Agent: Translate titles and summaries - OpenRouter Chat Model: Provide LLM capabilities for translation - Telegram: Send formatted digest to chat ## Known pitfalls, handle each one explicitly in your implementation 1. Telegram message length exceeds 4096 characters easily with multiple posts, so split long digests into separate messages. 2. OpenRouter model latency may delay the digest delivery, consider caching summaries or using a faster model endpoint. 3. HTML tags in post titles can break the Telegram formatting, strip all HTML entities before sending to the API. ## Reference implementation https://n8n.io/workflows/12748 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/hacker-news-trends-to-telegram/ via usecasesforagents.com
Frequently asked questions
Can I use a different LLM than OpenRouter?
Yes. OpenRouter is only the example LLM in this recipe. The same flow works with Anthropic, Cohere, DeepSeek and Google Gemini. Swap the LLM connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for anyone who wants this off their own plate, no team or company required.