Pantheon

Enterprise-grade AI backend system with Windows VM integration, multi-model AI support, and OAuth authentication.

Platform Demo

The demo shows the complete Pantheon platform including project creation, Windows VM management, and AI model integration.

Table of Contents

• Overview
• Features
• Architecture
• Prerequisites
• Quick Start
• Installation Guide
• Configuration
  • Environment Setup
  • Keycloak Configuration
  • Model Configuration
• Deployment Guide
• Usage Guide
• API Documentation
• Network Architecture
• Troubleshooting
• Contributing
• License

Overview

Pantheon is a comprehensive AI backend platform designed for enterprise deployments. It provides a unified interface for multiple AI models, secure Windows VM management, and enterprise-grade authentication.

Key Capabilities

• Multi-Model AI Integration: Seamlessly integrate with OpenRouter, Google Gemini, OpenAI, and Anthropic
• Windows VM Management: Create and manage isolated Windows 11 environments for AI agents
• Enterprise Authentication: OAuth 2.0 via Keycloak with support for Google, Microsoft, and custom providers
• Secure Architecture: Network isolation, encrypted communications, and row-level security
• Scalable Design: Docker-based deployment with horizontal and vertical scaling support

Features

Core Features

Feature	Description	Documentation
Multi-Model AI	Support for 100+ AI models through unified API	Model Configuration
Windows VM	Isolated Windows 11 VMs with MCP protocol	Usage Guide
Authentication	OAuth 2.0 with Keycloak	Keycloak Setup
Database	PostgreSQL with automatic migrations	Installation Guide
Network Isolation	Project-based network segmentation	Network Architecture
API Management	User-specific API keys with usage tracking	API Documentation

Technical Features

• Docker containerization with health monitoring
• Static IP addressing for reliable service discovery
• Multi-homed containers for cross-network communication
• Automatic database schema migrations
• Real-time collaboration via WebSocket
• Comprehensive audit logging
• Encrypted API key storage

Architecture

System Overview

┌─────────────────────────────────────────────────────────────┐
│                     Main Network (10.0.1.0/24)              │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐  │
│  │ Frontend │  │ Backend  │  │ Keycloak │  │ Postgres │  │
│  │ :3000    │  │ :3002    │  │ :8080    │  │ :5432    │  │
│  └──────────┘  └──────────┘  └──────────┘  └──────────┘  │
│                                                             │
└─────────────────────────────────────────────────────────────┘
                           │
                           │ Multi-homed Bridge
                           ▼
┌─────────────────────────────────────────────────────────────┐
│              Project Network (172.30.x.0/24)                │
│                      (Isolated per Project)                 │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐  │
│  │ Windows  │  │  Shared  │  │  Tools   │  │ Backend  │  │
│  │   VM     │  │  Folder  │  │   API    │  │(bridge)  │  │
│  └──────────┘  └──────────┘  └──────────┘  └──────────┘  │
│                                                             │
└─────────────────────────────────────────────────────────────┘

For detailed architecture information, see Network Architecture.

Prerequisites

System Requirements

• Operating System: Windows 10/11, macOS 10.15+, or Linux (Ubuntu 20.04+)
• Docker: Docker Desktop 4.0+ or Docker Engine 20.10+
• Memory: 8GB RAM minimum, 16GB recommended
• Storage: 50GB free disk space
• Network: Internet connection for pulling images and API access

Required Accounts

Service	Purpose	Sign Up Link
DockerHub	Pull container images	hub.docker.com
OpenRouter	Multi-model AI access	openrouter.ai
Google AI Studio	Gemini API access	makersuite.google.com

Optional Accounts

Service	Purpose	Sign Up Link
OpenAI	GPT models	platform.openai.com
Anthropic	Claude models	console.anthropic.com

Quick Start

1. Clone Repository

git clone https://github.com/akilhassane/pantheon.git
cd pantheon

2. Configure Environment

# Copy environment template
cp .env.example .env

# Edit with your API keys
nano .env  # Linux/Mac
notepad .env  # Windows

Required configuration:

OPENROUTER_API_KEY=your_openrouter_key_here
GEMINI_API_KEY=your_gemini_key_here
MCP_MASTER_SECRET=generate_random_64_character_string
POSTGRES_PASSWORD=secure_database_password

3. Deploy

Windows:

.\deploy.ps1

Linux/Mac:

chmod +x deploy.sh
./deploy.sh

4. Access Services

• Frontend: http://localhost:3000
• Backend API: http://localhost:3002
• Keycloak Admin: http://localhost:8080
  • Username: admin
  • Password: admin (change in production)

5. Uninstall (The Doofenshmirtz)

To completely remove Pantheon from your system:

Windows:

.\the-doofenshmirtz.ps1

Linux/Mac:

chmod +x the-doofenshmirtz.sh
./the-doofenshmirtz.sh

Options:

• --keep-images: Keep Docker images
• --keep-volumes: Keep data volumes (preserves database)
• --force: Skip confirmation prompt

6. Next Steps

1. Configure Keycloak OAuth providers
2. Set up AI models
3. Create your first project

Documentation

Getting Started

• Installation Guide - Complete installation instructions
• Configuration Guide - Environment and service configuration

Configuration

• Keycloak Setup - OAuth provider configuration
• Model Configuration - AI model setup and selection

Usage

• Usage Guide - Complete user guide
• API Documentation - REST and WebSocket API reference

Operations

• Troubleshooting - Common issues and solutions

Contributing

We welcome contributions! To contribute:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

Please ensure your code follows the existing style and includes appropriate tests.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Support

Getting Help

• Documentation: GitHub Wiki
• Issues: GitHub Issues
• Discussions: GitHub Discussions

Reporting Issues

When reporting issues, please include:

1. System information (OS, Docker version)
2. Steps to reproduce
3. Expected vs actual behavior
4. Relevant logs
5. Configuration (sanitized)

Acknowledgments

• OpenRouter - Multi-model AI access
• Keycloak - Identity and access management
• Docker - Containerization platform
• PostgreSQL - Database system
• Next.js - React framework

Project Status

• Version: 1.0.0
• Status: Production Ready
• Last Updated: 2026-02-23
• Maintained: Yes