An intelligent, automated tech news aggregation and summarization tool that delivers concise TL;DR summaries from major tech publications every 12 hours.

# Clone and setup
git clone <your-repository-url>
cd tech-news-digest
pip install -r requirements.txt

# Set API key
export OPENROUTER_API_KEY="your-openrouter-api-key"

# Generate your first digest
python generate_digest.py

• Python 3.12+ - Download here
• OpenRouter API Key - Get yours here
• Git (for cloning and automation)

1. Clone the repository:

   git clone <your-repository-url>
   cd tech-news-digest

2. Create a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

   pip install openai feedparser requests beautifulsoup4

   Or create a requirements.txt:

   openai>=1.0.0
   feedparser>=6.0.0
   requests>=2.31.0
   beautifulsoup4>=4.12.0

4. Configure your API key:

   # Option 1: Environment variable
   export OPENROUTER_API_KEY="your-api-key-here"
   
   # Option 2: Create .env file (add to .gitignore!)
   echo "OPENROUTER_API_KEY=your-api-key-here" > .env

1. Add repository secret:

   • Go to Settings → Secrets and variables → Actions
   • Click New repository secret
   • Name: OPENROUTER_API_KEY
   • Value: Your OpenRouter API key

2. Enable Actions:

   • Go to Actions tab
   • Click I understand my workflows, go ahead and enable them

3. Manual trigger (optional):

   • Actions tab → Tech News Digest → Run workflow

# Basic usage
python generate_digest.py

# The script will:
# 1. Fetch headlines from all configured sources
# 2. Generate AI summary using Gemini 2.5 Flash
# 3. Save to news_digests/digest_YYYY-MM-DD_HH-MM.txt
# 4. Display results in terminal

Starting tech news digest generation...
Fetching headlines from The Verge...
Fetching headlines from TechCrunch...
Fetching headlines from CNET...
Generating summary with LLM...

==================================================
TECH NEWS DIGEST GENERATED
==================================================

Tech News Digest - 2024-01-15 02:30 PM
==================================================

🚀 **Major Product Launches**
• Apple announces new MacBook Pro with M4 chip
• Google releases Gemini Advanced with improved coding

📱 **Mobile & Hardware**
• Samsung Galaxy S25 leaked specifications surface
• iPhone 16 sales exceed expectations in Q4

🤖 **AI & Machine Learning**
• OpenAI unveils GPT-5 preview for developers
• Microsoft integrates Copilot into more Office apps

==================================================

Successfully wrote the digest to news_digests/digest_2024-01-15_14-30.txt
Tech news digest generation completed successfully!

Edit the feeds list in generate_digest.py:

feeds = [
    ("Your Source", "https://example.com/rss.xml"),
    ("The Verge", "https://www.theverge.com/rss/index.xml"),
    # Add more sources here
]

Change the model in generate_digest.py:

# Available models on OpenRouter:
MODEL = "google/gemini-2.5-flash"      # Current (fast, cost-effective)
MODEL = "anthropic/claude-sonnet-4"    # Alternative (higher quality)
MODEL = "openai/gpt-4"                 # Alternative (reliable)

Modify the cron expression in .github/workflows/tech-news.yml:

schedule:
  # Every 12 hours (current)
  - cron: '0 */12 * * *'
  
  # Every 6 hours
  # - cron: '0 */6 * * *'
  
  # Daily at 9 AM UTC
  # - cron: '0 9 * * *'
  
  # Weekdays only at 9 AM UTC
  # - cron: '0 9 * * 1-5'

Adjust the AI prompt for different summary styles:

# In generate_tech_news_digest(), modify the system message:
"content": f"""You are a tech news summarizer focused on [YOUR FOCUS AREA].
Create summaries that emphasize [YOUR PREFERENCES].
Target audience: [YOUR AUDIENCE]
Style: [FORMAL/CASUAL/TECHNICAL]"""

tech-news-digest/
├── generate_digest.py          # Main script
├── .github/
│   └── workflows/
│       └── tech-news.yml      # GitHub Actions workflow
├── news_digests/              # Generated digest files
│   ├── digest_2024-01-15_14-30.txt
│   ├── digest_2024-01-15_02-30.txt
│   └── ...
├── requirements.txt           # Python dependencies
├── README.md                  # This file
├── .gitignore                # Git ignore rules
└── .env.example              # Environment template

The script includes comprehensive error handling:

# Automatic fallback chain:
RSS Feeds → Web Scraping → Graceful Error Messages

# Exit codes:
# 0: Success
# 1: Critical error (API key missing, file write failure, etc.)

# Pipe output to other tools
python generate_digest.py > daily_digest.txt

# Run with custom timestamp
python generate_digest.py && echo "Digest generated at $(date)"

# Integration with cron (alternative to GitHub Actions)
0 */12 * * * cd /path/to/tech-news-digest && python generate_digest.py

Monitor your OpenRouter usage:

# The script uses these parameters for cost optimization:
max_tokens=1024        # Reasonable limit for summaries
temperature=0.3        # Consistent, focused output
model="gemini-2.5-flash"  # Cost-effective choice

Enable detailed logging by modifying the script:

import logging
logging.basicConfig(level=logging.DEBUG)

# Add this at the start of generate_digest.py

Test individual components:

# Test RSS feed access
python -c "import feedparser; print(len(feedparser.parse('https://www.theverge.com/rss/index.xml').entries))"

# Test OpenRouter connection
python -c "import openai; client = openai.OpenAI(base_url='https://openrouter.ai/api/v1', api_key='your-key'); print('Connection OK')"

We welcome contributions! Here's how to help:

git clone <your-fork>
cd tech-news-digest
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
pip install pytest black flake8  # Development tools

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Test your changes thoroughly
4. Format code: black generate_digest.py
5. Lint code: flake8 generate_digest.py
6. Commit changes: git commit -m 'Add amazing feature'
7. Push to branch: git push origin feature/amazing-feature
8. Submit a Pull Request

• 📰 Add new news sources
• 🎨 Improve summary formatting
• 🔧 Add configuration file support
• 📊 Add analytics/statistics
• 🌐 Add internationalization
• 📱 Create web interface
• 🔔 Add notification systems

• Runtime: 30-60 seconds per execution
• API calls: 1 per run (batch processing)
• Storage: ~2-5KB per digest file
• Bandwidth: ~100-500KB per run