GEM - WolfTech Innovations

Autonomous AI Code Generator with Modern Web UI

Zero-explanation code generation powered by Ollama

---

🚀 Quick Start

docker run -d -p 8080:5000 wolftechinnovations/gem:latest

Access: http://localhost:8080

---

📋 Features

• Modern Monochrome UI - Clean white-on-black interface
• Multi-Project Management - Organize code by project
• Real-Time Generation - Watch code appear live
• Smart File Detection - Auto-detects languages and filenames
• Persistent Storage - Projects saved automatically
• One-Click Downloads - Export generated files instantly
• No API Keys Required - Runs entirely local

---

🐳 Docker Usage

Basic Run

docker run -d -p 8080:5000 wolftechinnovations/gem:latest

With Persistent Storage

docker run -d \
  -p 8080:5000 \
  -v $(pwd)/projects:/app/projects \
  wolftechinnovations/gem:latest

Custom Port

docker run -d -p 3000:5000 wolftechinnovations/gem:latest

---

💡 How to Use

1. Open Browser → http://localhost:8080
2. Click NEW → Create a project
3. Enter Prompt → "Make a Python web scraper"
4. Click GENERATE → Watch code appear
5. Download Files → Click any file to download

---

📝 Example Prompts

Make a hello world program in python

Create a React todo app with localStorage

// App.jsx
// TodoList.jsx
// styles.css

Build a REST API in Express.js with user CRUD operations

Create a Python web scraper for news headlines with BeautifulSoup

---

🗂️ Multi-File Projects

Use // filename.ext markers to specify multiple files:

Prompt:

Create a web app

// index.html
// script.js
// style.css

Output:

• index.html
• script.js
• style.css

---

🛠️ Build from Source

# Clone repository
git clone https://github.com/wolftechinnovations/gem
cd gem

# Build image
docker build -t wolftechinnovations/gem:latest .

# Run
docker run -d -p 8080:5000 wolftechinnovations/gem:latest

---

🔧 Configuration

Environment Variable	Default	Description
PORT	5000	Internal Flask port
OLLAMA_HOST	0.0.0.0	Ollama service host

---

📦 Volume Mounts

Path	Purpose
/app/projects	Persistent project storage

Example:

docker run -d \
  -p 8080:5000 \
  -v /home/user/my-projects:/app/projects \
  wolftechinnovations/gem:latest

---

🎯 Model Information

Model: wolftech-innovations/Gem
Base: Gemma 2B
Type: Code-only output (no explanations)
Hub: https://ollama.com/wolftech-innovations/Gem

Characteristics:

• Outputs ONLY code
• Zero comments or explanations
• Maximum density
• Minimal variable names
• Compressed syntax

---

⚡ Performance

• First Run: ~30s (model download)
• Subsequent Runs: ~5s (cached)
• Generation Speed: 2-10s depending on complexity
• RAM Usage: ~2GB with model loaded

---

🔍 Troubleshooting

Port Already in Use

docker run -d -p 9000:5000 wolftechinnovations/gem:latest

Model Not Loading

docker logs <container-id>

Reset Projects

docker run -d -p 8080:5000 wolftechinnovations/gem:latest
# Projects auto-clear on new container

Access Logs

docker exec -it <container-id> tail -f /var/log/ollama.log

---

🌐 Browser Compatibility

• ✅ Chrome/Edge (Recommended)
• ✅ Firefox
• ✅ Safari
• ✅ Opera

---

📊 System Requirements

Minimum:

• 4GB RAM
• 2 CPU cores
• 5GB disk space

Recommended:

• 8GB RAM
• 4 CPU cores
• 10GB disk space

---

🔐 Security

• Local Only - No external API calls
• No Telemetry - Zero data collection
• Isolated - Runs in Docker container
• No Auth Required - Single-user design

---

📄 License

MIT License - See LICENSE file

---

🤝 Contributing

Issues and PRs welcome at:
https://github.com/wolftechinnovations/gem

---

📞 Support

• Issues: GitHub Issues
• Docs: https://docs.wolftechinnovations.com
• Model: https://ollama.com/wolftech-innovations/Gem

---

🎉 Credits

Created by: WolfTech Innovations
Powered by: Ollama, Flask, Gemma 2B
Philosophy: Maximum density, zero explanations

---

Made with ⚡ by WolfTech Innovations