⭐ SEO Keyword Clusters (Legacy Project)

⚠️ This repository is archived and represents an early prototype of what eventually became SEOCluster.ai. It is preserved for educational and historical purposes only.

---

🚀 Try the New Production Platform: SEOCluster.ai

A modern AI-powered SaaS for keyword clustering, content briefs, and automated landing pages.

👉 https://seocluster.ai

Highlights of the new platform:

• ⚡ FastAPI backend + Next.js frontend
• 🔥 SentenceTransformer embeddings (no more classic KMeans)
• 🌍 Local-intent detection across 325k+ global locations
• 📝 AI-generated content briefs
• 🧱 Landing page generator
• 🔐 Firebase authentication
• 💳 Stripe billing (Free, Pro, Agency tiers)
• 📊 Google Search Console OAuth integration
• 🚀 Cloud Run multi-worker deployment
• 🧠 Smart caching & optimized UX

This legacy repo does not include these features — it represents the origins of the project.

---

📚 About This Legacy Version

This codebase was originally created between 2021–2022 for a UWA Data Science Capstone project.

It uses:

• Python + Flask
• Pandas & scikit-learn
• Traditional KMeans clustering
• TF-IDF cluster labeling
• Google Data Studio + Tableau for visualization
• CSV export from Google Search Console
• Basic SQLite storage

📌 This version is not production-ready.

---

📦 Repository Structure

.
├── app.py                    # Legacy Flask app
├── Keyword_Clustering.ipynb  # Main ML notebook
├── Queries.csv               # Sample GSC query data
├── static/                   # Static assets
├── templates/                # Jinja2 templates
├── keyword_clustering.sqlite # Example database
└── README.md

---

🏛 License & Usage

This legacy version is open for learning and academic use only.

✔️ Allowed:

• Personal study
• Academic use
• ML experimentation

❌ Not Allowed:

• Commercial use
• Using this code in SaaS products
• Replicating SEOCluster.ai features
• Redistributing modified versions for business use

For production use → 👉 https://seocluster.ai

📜 Project History

This repository represents the earliest foundation of SEOCluster.ai.

• 2021 – Built as a Data Science ML project
• 2022 – First UI deployed to Heroku
• 2023–2024 – Rewritten using modern full-stack architecture
• 2024–2025 – Became SEOCluster.ai, a full SaaS platform

The repository remains public because:

• It already has ⭐ stars and forks
• It helps others learn ML-based clustering
• It documents the evolution of the project

⭐ Support the Journey

If you're interested in how this evolved into a real SaaS business, consider:

• ⭐ Starring this repo
• 🚀 Trying SEOCluster.ai → https://seocluster.ai
• 💬 Connecting for collaboration

🔗 Useful Links

• Current SaaS: https://seocluster.ai