AutoGram is an intelligent AI agent that automates AI news curation and Instagram content management. It seamlessly collects tech news, generates engaging visuals, and maintains your social media presence - all on autopilot.

View this post on Instagram

A post shared by Muhammad Abdullah (@ranahaani.me)

• Smart News Aggregation: Automatically collects and filters AI & tech news
• AI-Powered Content Creation: Generates unique, branded images for each post
• Automated Instagram Management: Handles posting and scheduling
• Performance Analytics: Tracks engagement and optimizes content strategy
• Self-Learning: Improves content selection based on performance
• Brand Consistency: Maintains your visual identity across all posts
• Multi-Model Image Generation: Supports both OpenAI GPT Image and Replicate models

• Core Engine: Python 3.9+
• AI Services:
  • Google Gemini (content analysis)
  • OpenAI GPT Image (primary image generation)
  • Replicate ideogram (alternative image generation)
• News Sources: GNews API
• Social Platform: Instagram API
• Processing: aiohttp, asyncio
• Validation: Pydantic
• Image Handling: Pillow

1. Clone & Install

git clone https://github.com/ranahaani/autogram.git
cd autogram
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

2. Configure Environment

# Create .env file
cp .env.example .env

# Add your API keys
GEMINI_API_KEY=your_key_here
OPENAI_API_KEY=your_openai_key_here
REPLICATE_API_TOKEN=your_token_here
IG_USERNAME=your_username
IG_PASSWORD=your_password

3. Configure Agent

// config.json
{
    "name": "AutoGram",
    "post_frequency": 3,
    "max_news_age": 24,
    "output_dir": "./output",
    "brand_theme": {
        "primary_color": "#FF6B6B",
        "secondary_color": "#4ECDC4",
        "font_style": "modern"
    },
    "image_generation": {
        "default_provider": "openai",
        "providers": {
            "openai": {
                "model": "gpt-image-1",
                "size": "1024x1024",
                "quality": "medium"
            },
            "replicate": {
                "model": "ideogram-ai/ideogram-v2"
            }
        }
    }
}

4. Launch

python main.py

📈 Performance Metrics
- Posts Created: 125
- Engagement Rate: 3.2%
- Top Performing Topics: AI, Machine Learning, Tech Innovation
- Average Likes: 234
- Comment Rate: 2.1%

You can configure which AI model to use for image generation in config.json:

1. OpenAI GPT Image (Default)

{
    "image_generation": {
        "default_provider": "openai",
        "providers": {
            "openai": {
                "model": "gpt-image-1",
                "size": "1024x1024",
                "quality": "medium"
            }
        }
    }
}

2. Replicate Ideogram

{
    "image_generation": {
        "default_provider": "replicate",
        "providers": {
            "replicate": {
                "model": "ideogram-ai/ideogram-v2"
            }
        }
    }
}

class NewsSource:
    async def fetch(self) -> List[NewsItem]:
        # Your custom news source logic
        pass

TEMPLATES = {
    "tech_news": "Modern minimalist tech visualization: {title}",
    "ai_update": "Futuristic AI concept representing: {content}",
    "innovation": "Creative tech breakthrough visual for: {topic}"
}

graph LR
    A[News Collection] --> B[AI Analysis]
    B --> C[Content Generation]
    C --> D[Image Creation]
    D --> E[Instagram Posting]
    E --> F[Performance Analysis]
    F --> A

AutoGram includes robust error handling:

• Automatic retry mechanisms
• Graceful degradation
• State persistence
• Error notifications
• Performance monitoring

📸 Generated Post Example:
- Title: "Breaking: New AI Model Achieves Human-Level Performance"
- Image: Modern tech visualization (via OpenAI GPT Image)
- Hashtags: #AI #TechNews #Innovation #FutureOfTech
- Engagement: 543 likes, 27 comments

1. Content Strategy

   • Post during peak engagement hours
   • Maintain consistent branding
   • Use trending hashtags
   • Monitor performance metrics

2. System Management

   • Regular log monitoring
   • Backup configuration files
   • Update API keys periodically
   • Monitor resource usage

• Multi-model image generation support
• AI-powered hashtag optimization
• Advanced analytics dashboard
• Custom template builder
• Engagement automation
• A/B testing system

Contributions are welcome! Please read our Contributing Guidelines for details on our code of conduct and the process for submitting pull requests.

AutoGram is licensed under the MIT License - see the LICENSE file for details.