You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
AI-powered Social Media Marketing Automation platform with multi-agent workflows using LangGraph, Gemini, and Nano Banana Pro (Gemini 3 Pro Image Preview).
# Install dependencies
npm install
# Configure environment
cp .env.example .env
# Edit .env with your API keys# Start development server
npm run dev
# Start production server
npm start
curl -X POST http://localhost:3000/api/content/feedback \
-H "Content-Type: application/json" \
-d '{ "postId": "POST_ID_HERE", "feedback": "Make the tone more casual and add more emojis" }'
Environment Variables
Variable
Description
GEMINI_API_KEY
Google Gemini API key (also used for Nano Banana Pro image generation)
GEMINI_MODEL
Gemini model name (default: gemini-1.5-pro)
DATABASE_URL
MongoDB connection string
CLOUDINARY_CLOUD_NAME
Cloudinary cloud name
CLOUDINARY_API_KEY
Cloudinary API key
CLOUDINARY_API_SECRET
Cloudinary API secret
INSTAGRAM_ACCESS_TOKEN
Instagram Graph API token
LINKEDIN_ACCESS_TOKEN
LinkedIn API token
LINKEDIN_PERSON_URN
LinkedIn person URN (e.g. urn:li:person:abc123)
TWITTER_API_KEY
Twitter/X OAuth 2.0 user access token
PORT
Server port (default: 3000)
NODE_ENV
Environment (development/production)
📖 For detailed step-by-step setup of each platform API, see PLATFORM_SETUP.md
Tech Stack
Runtime: Node.js (ES Modules)
Framework: Express.js
AI/LLM: LangChain + Google Gemini
Workflows: LangGraph
Image Gen: Nano Banana Pro (gemini-3-pro-image-preview via @google/genai SDK)