RSS to Telegram, a daily news digest you will read
Checking five feeds turns into twenty tabs. Then you “save for later,” forget, and end the day feeling oddly behind on the one topic you care about most.
This RSS Telegram digest problem hits marketing leads who need quick context for campaigns, but agency owners and busy founders feel it too. You don’t need more news. You need a daily recap you can actually finish.
This workflow collects yesterday’s articles from several RSS feeds, summarizes each one locally with Ollama, and posts a clean digest to Telegram. You’ll see what it does, what you need, and what to tweak so it matches your routine.
How This Automation Works
See how this solves the problem:
n8n Workflow Template: RSS to Telegram, a daily news digest you will read
flowchart LR
subgraph sg0["Scheduled Daily Kickoff Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Scheduled Daily Kickoff", pos: "b", h: 48 }
n1@{ icon: "mdi:cog", form: "rounded", label: "Fetch RSS AI Techpark", pos: "b", h: 48 }
n2@{ icon: "mdi:cog", form: "rounded", label: "Fetch RSS KnowTechie", pos: "b", h: 48 }
n3@{ icon: "mdi:cog", form: "rounded", label: "Fetch RSS AI Business", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Fetch RSS Guardian AI", pos: "b", h: 48 }
n5@{ icon: "mdi:cog", form: "rounded", label: "Fetch RSS Hugging Face", pos: "b", h: 48 }
n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Consolidate RSS Streams"]
n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "Pick RSS Attributes", pos: "b", h: 48 }
n8@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Filter Prior Day Articles", pos: "b", h: 48 }
n9@{ icon: "mdi:robot", form: "rounded", label: "Generate Ollama Summary", pos: "b", h: 48 }
n10@{ icon: "mdi:robot", form: "rounded", label: "Ollama LLM Engine", pos: "b", h: 48 }
n11["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Merge Summary with Source"]
n12@{ icon: "mdi:swap-vertical", form: "rounded", label: "Assemble Message Fields", pos: "b", h: 48 }
n13["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Dispatch Telegram Digest"]
n10 -.-> n9
n6 --> n7
n0 --> n2
n0 --> n1
n0 --> n3
n0 --> n4
n0 --> n5
n7 --> n8
n3 --> n6
n2 --> n6
n1 --> n6
n5 --> n6
n4 --> n6
n8 --> n9
n8 --> n11
n12 --> n13
n9 --> n11
n11 --> n12
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n0 trigger
class n9,n10 ai
class n8 decision
classDef customIcon fill:none,stroke:none
class n6,n11,n13 customIcon
The Challenge: Keeping up without living in your browser
News via RSS sounds simple until you try to keep it “daily.” One feed becomes three. Then five. You open a few posts, skim the first paragraphs, and realize you still don’t know what mattered. Worse, your “system” relies on you doing the same ritual every day, at the exact moment you have the least mental energy. That’s how good sources turn into background noise. And when you miss the story that would’ve changed your decision, it stings because the fix is painfully obvious: stop making your brain do the sorting.
The friction compounds. Here’s where it breaks down in real life.
- Skimming multiple sites burns about an hour a day, and you still feel unsure about what you read.
- RSS readers pile up unread items, so “catching up” becomes a weekend chore you never do.
- Manually copying links into Slack or Telegram is easy to forget, which means the team never sees the same context.
- Cloud summarizers are convenient, but many teams hesitate to send full article text off-device.
The Fix: A daily Telegram digest built from RSS and local summaries
This n8n workflow runs on a daily schedule and pulls fresh items from several RSS feeds (AI TechPark, KnowTechie, AI Business, Guardian AI, and Hugging Face). It then keeps only the articles published yesterday, so you get a true recap instead of an endless stream. For each article, the workflow sends the content to your local Ollama server (for example, a Raspberry Pi 5 running llama3.2) and generates a short, readable summary without relying on paid APIs. Finally, it formats everything into a clean Telegram message that includes the title, author when available, and the original link. Open Telegram once, scan fast, move on. Honestly, that’s the whole point.
The workflow starts with a daily kickoff in n8n. From there, it collects items from multiple RSS sources, filters them to “yesterday only,” and summarizes them with a local LLM in Ollama. At the end, Telegram receives a digest that reads like a briefing, not a data dump.
What Changes: Before vs. After
| What This Eliminates | Impact You’ll See |
|---|---|
|
|
Real-World Impact
Say you follow 5 AI feeds and you usually open 6 articles a day. If you spend maybe 10 minutes per article to skim, that’s about an hour daily (and that’s on a good day). With this workflow, you spend about 2 minutes in the morning skimming the Telegram digest, then open only the 1–2 links that truly matter. The reading time stays, but the “find and sort” time mostly disappears.
Requirements
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Ollama for local Llama 3.2 summaries.
- Telegram Bot to deliver the digest message.
- Telegram bot token (get it from BotFather in Telegram).
Skill level: Intermediate. You’ll connect Telegram credentials and run Ollama locally, but you won’t be writing code.
Need help implementing this? Talk to an automation expert (free 15-minute consultation).
The Workflow Flow
Daily kickoff in n8n. The workflow runs on a schedule so you don’t have to remember it. You pick the time, n8n handles the rest.
RSS collection across multiple sources. Several RSS Read steps pull in items from your chosen publications, then a merge combines them into a single stream so the rest of the workflow treats them the same.
Yesterday-only filtering. The workflow selects the fields you care about (title, link, author, publish date) and filters out anything not published the previous day. No backlog guilt.
Local AI summarization and Telegram delivery. Each remaining item is summarized by Ollama (Llama 3.2 in the provided setup), merged back with the source details, formatted into a readable digest, and sent to your Telegram chat via your bot.
You can easily modify the RSS sources to match your niche based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Scheduled Trigger
Set up the daily kickoff schedule that starts the RSS collection and digest flow.
- Open Scheduled Daily Kickoff and set the schedule rule to trigger at minute
1(Rule → Interval → Trigger At Minute). - Confirm your workflow timezone in settings if you need the daily run to align with local time (e.g.,
Europe/Madrid). - Optional: keep Flowpast Branding as a documentation sticky note for team context.
Step 2: Connect RSS Sources and Merge Streams
Configure all RSS feeds and combine them into a single unified stream for processing.
- In Scheduled Daily Kickoff, confirm it outputs to Fetch RSS KnowTechie, Fetch RSS AI Techpark, Fetch RSS AI Business, Fetch RSS Guardian AI, and Fetch RSS Hugging Face in parallel.
- Configure the five RSS nodes (grouped by function) with these URLs: Fetch RSS AI Techpark →
https://ai-techpark.com/category/ai/feed/, Fetch RSS KnowTechie →https://knowtechie.com/category/ai/feed/, Fetch RSS AI Business →https://aibusiness.com/rss.xml, Fetch RSS Guardian AI →https://www.theguardian.com/technology/artificialintelligenceai/rss, Fetch RSS Hugging Face →https://huggingface.co/blog/feed.xml. - Open Consolidate RSS Streams and set Number of Inputs to
5to match the five RSS sources.
Step 3: Normalize and Filter Articles
Extract the fields you need from each RSS item and filter to only yesterday’s news.
- In Pick RSS Attributes, add assignments for the normalized fields: title →
{{ $json.title }}, creator →{{ $json.creator }}, pubDate →{{ $json.pubDate }}, content →{{ $json.content }}, link →{{ $json.link }}. - In Filter Prior Day Articles, set the condition to compare Left Value
{{ new Date($json.pubDate).toISOString().slice(0,10) }}with Right Value{{ $today.minus({ days:1 }).toISODate() }}using the equals operator. - Confirm that Pick RSS Attributes outputs to Filter Prior Day Articles, which then sends items to both Generate Ollama Summary and Merge Summary with Source in parallel.
pubDate. If filtering drops valid items, check the feed timezone and your workflow timezone.Step 4: Set Up AI Summarization and Merge Results
Generate a formatted summary with Ollama and merge it back with the source article data.
- Open Generate Ollama Summary and set Text to the prompt:
Summarize this AI news in bullet points. Give only the result in this format: *📰 Title:* {{ $json.title }} *✍️ Author:* {{ $json.creator }} *🔗 Link:* {{ $json.link }} *🧠 Summary:* News text: {{ $json.content }}. - Ensure Generate Ollama Summary uses Ollama LLM Engine as its language model connection.
- In Ollama LLM Engine, set Model to
llama3.2:1b. - Open Merge Summary with Source and set Mode to
combineand Combine By tocombineByPositionso the summary aligns with the original item.
Credential Required: Connect your ollamaApi credentials in Ollama LLM Engine. Generate Ollama Summary uses Ollama LLM Engine as the language model, so credentials must be added to Ollama LLM Engine, not the chain node.
Step 5: Assemble the Telegram Message and Dispatch
Map the final fields and send the digest to Telegram in HTML format.
- In Assemble Message Fields, set the final fields: Title →
{{ $json.title }}, Author →{{ $json.creator }}, Publication date →{{ $json.pubDate }}, Summary →{{ $json.text }}, Link →{{ $json.link }}. - Open Dispatch Telegram Digest and set Text to
Hello! I have here one interesting summary for you: <b>Title:</b> {{ $json.Title }} <b>Author:</b> {{ $json.Author }} <b>Publication date:</b> {{ $json["Publication date"] }} <b>News link:</b> {{ $json.Link }} <b>Summary:</b> {{ $json.Summary }}. - In Dispatch Telegram Digest, set Chat ID to your target Telegram chat or channel ID (currently blank).
- Confirm additional fields include Parse Mode
HTMLand Disable Web Page Previewtrue.
Credential Required: Connect your telegramApi credentials in Dispatch Telegram Digest.
Step 6: Test and Activate Your Workflow
Run a manual test to verify the digest format and then activate for daily delivery.
- Click Execute Workflow and verify that at least one item passes Filter Prior Day Articles.
- Check that Generate Ollama Summary returns a formatted summary and that Merge Summary with Source combines it with the source fields.
- Confirm Dispatch Telegram Digest sends a message with Title, Author, Publication date, News link, and Summary.
- Toggle the workflow to Active to enable the daily schedule.
Watch Out For
- Telegram credentials can expire or need specific permissions. If things break, check the bot token and chat ID configuration in your n8n Telegram credentials first.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Common Questions
About an hour if Ollama and Telegram are already set up.
Yes, but you’ll want someone comfortable with basic setup. You mainly connect accounts, paste RSS URLs, and point the workflow at your local Ollama server.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Ollama costs, which are usually just your hardware and electricity since it runs locally.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Swap the RSS Read sources to match your industry, then adjust the prompt in the “Generate Ollama Summary” step so the summaries come out in your style. Many teams switch from bullet summaries to a single short paragraph, or add a “Why it matters” line for decision-makers. If you want a weekly roundup instead of daily, change the Scheduled Daily Kickoff timing and tweak the “Filter Prior Day Articles” logic to look back further.
Usually it’s the chat ID or an outdated bot token. Regenerate the token via BotFather if needed, then update the credential in n8n and re-check the numeric chat ID (group chats are the common gotcha). Also confirm the bot is allowed to post in that chat, because Telegram can block messages if permissions aren’t right.
It depends mostly on your hardware because Ollama does the heavy lifting. On a typical small server, a handful of feeds and a few dozen articles per run is fine, but if you try to summarize hundreds of items daily you’ll feel it in runtime. n8n Cloud plans have execution limits by tier; self-hosting has no fixed execution cap (your server becomes the limit).
For local AI summarization, usually yes. Zapier and Make are great for simple “new RSS item → send message” tasks, but they’re not designed around running an on-device model like Ollama, and complex filtering/merging gets messy fast. n8n also gives you more control over how you merge multiple feeds and how you format a single digest message. If privacy matters, self-hosting is a big deal. If you only want to forward headlines with no summarization, a simpler tool can be enough. Talk to an automation expert if you’re not sure which fits.
Once this is running, your daily reading becomes a single message, not a pile of tabs. Set it up, let it run, and use the regained attention for work that actually moves.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
