An n8n workflow that watches my blog RSS feed, summarizes new posts with a local LLM (Gemma on Ollama), and cross-posts to Facebook, LinkedIn, X, and Instagram. I write the post once; the workflow handles the rest.
Overview
| Aspect | Details |
|---|---|
| Platform | Self-hosted n8n |
| LLM | Gemma via Ollama (local GPU) |
| Social APIs | Postiz |
| Scheduling | Cron trigger (10 min) |
| Hardware | RTX 3090 Ti for inference |
How It Works
- Fetch - RSS feed polling for new blog posts
- Dedupe - Hash-based tracking skips already-posted entries before any further work
- Summarize - Ollama (Gemma) generates platform-specific summaries
- Extract - Parse HTML for images, download and resize
- Generate - AI creates relevant hashtags
- Publish - Postiz API posts to all platforms
Architecture
┌─────────────────────────────────────────────────────────────────┐
│ Hugo RSS Feed │
└───────────────────────────┬─────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ n8n Workflow │
│ ┌──────────────────────────────────────────────────────────┐ │
│ │ Cron Trigger (10 min) │ │
│ └──────────────────────────┬───────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────▼───────────────────────────────┐ │
│ │ RSS Feed Node (Fetch Latest) │ │
│ └──────────────────────────┬───────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────▼───────────────────────────────┐ │
│ │ Hash Check (Duplicate Prevention) │ │
│ └──────────────────────────┬───────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────▼───────────────────────────────┐ │
│ │ Ollama Node (Gemma LLM) │ │
│ │ • Summarize (platform char limits) │ │
│ │ • Generate hashtags │ │
│ └──────────────────────────┬───────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────▼───────────────────────────────┐ │
│ │ Image Extraction & Processing │ │
│ │ • HTML parsing │ │
│ │ • Download & resize │ │
│ └──────────────────────────┬───────────────────────────────┘ │
│ │ │
│ ┌──────────────────────────▼───────────────────────────────┐ │
│ │ Postiz API │ │
│ │ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │ │
│ │ │Facebook │ │LinkedIn │ │ X │ │Instagram│ │ │
│ │ └─────────┘ └─────────┘ └─────────┘ └─────────┘ │ │
│ └──────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
What Was Harder Than Expected
Getting the LLM to respect character limits was the recurring headache. X needs 280 characters, LinkedIn gets more room. The prompt engineering for consistent output length took more iteration than the actual workflow logic.
Postiz’s API has quirks — Instagram JSON handling in particular required workarounds that aren’t documented. The LLM output parsing needed to be fault-tolerant because Gemma occasionally returns slightly different JSON structures.
Duplicate prevention uses a simple link hash stored in a file. It works. The whole thing runs on the local RTX 3090 Ti — no API calls to OpenAI or anyone else.
Tech Stack
| Component | Technology |
|---|---|
| Automation | Self-hosted n8n with community nodes |
| AI | Gemma via Ollama |
| Social API | Postiz |
| Content | RSS feed parsing |
| Images | HTML parsing, HTTP download, resize |
| Deduplication | JavaScript hash with file tracking |
| Scheduling | Cron trigger |
The workflow is available as a template on n8n.io for anyone who wants to set up something similar.
Thanks to Grok (xAI) for help with debugging and optimization