GameX Engine

GameX Engine is a comprehensive AI-driven game development platform designed to streamline the creation of game narratives, assets, and world-building elements. It leverages advanced LLMs and agentic workflows to generate everything from initial game concepts to detailed questlines and 3D visual assets.

🚀 Features

🌌 SagaAgent: Narrative Generation Pipeline

Powered by LangGraph, the SagaAgent creates deep, interconnected game worlds through a multi-stage, human-in-the-loop workflow:

1. Concept: Generates core game ideas, genres, and USPs.
2. World Lore: Builds history, geography, and magic/tech systems.
3. Factions: Creates political groups, ideologies, and reputation dynamics.
4. Characters: Generates protagonists and NPCs tied to factions/lore.
5. Plot Arcs: Designs branching main stories with multiple endings.
6. Questlines: Develops specific missions and objectives.
7. RenderPrep: Prepares visual prompts for asset generation.

🎨 Asset Generation

• Visual Assets: Integrated pipelines for generating character concepts and environment art.
• 3D Models: Capabilities to generate 3D assets (GLB) from textual descriptions or images.

🧠 Intelligent Orchestration

• Research Agent: Performs deep web research to ground game concepts in reality or existing fiction styles.
• Supervisor Agent: Manages state and routes tasks between specialized agents.
• Memory Persistence: Checkpoint system to save/resume generation sessions and allow iterative feedback.

---

🏗️ Architecture

The project is divided into two main components:

• Frontend (/web): A modern Next.js 16 application (React 19) providing an interactive dashboard for managing workflows, viewing generated content, and visualizing assets.
• Backend (/backend): A FastAPI server that hosts the AI agents, manages sessions, and handles specific generation tasks using Python, LangChain, and LangGraph.

---

🛠️ Prerequisites

• Node.js (v18 or higher)
• Python (v3.10 or higher)
• uv (Python package manager, recommended) or pip
• API Keys:
  • Run backend/README.md for specific key requirements (OpenAI/Nebius, Google Gemini, HuggingFace).

---

🏁 Getting Started

1. Backend Setup

1. Navigate to the backend directory:

   cd backend

2. Create a Virtual Environment (using uv is recommended):

   pip install uv
   uv venv

3. Activate the environment:

   • Windows: .venv\Scripts\activate
   • Mac/Linux: source .venv/bin/activate

4. Install Dependencies:

   uv pip install -r requirements.txt

5. Configure Environment Variables: Create a .env file in the backend or root directory with the following keys:

   # AI Providers
   GOOGLE_API_KEY=your_gemini_key
   NEBIUS_API_KEY=your_nebius_key
   OPENAI_API_KEY=your_openai_key  # Optional if using Nebius for OpenAI-compatible endpoint
   HUGGINGFACE_API_KEY=your_hf_key
   
   # Configuration
   MODEL=openai/gpt-oss-120b # or other preferred model

6. Run the Server:

   # Run from root or backend directory ensuring paths are correct
   python backend/main.py

   The API will be available at http://localhost:8000.

2. Frontend Setup

1. Navigate to the web directory:

   cd web

2. Install Dependencies:

   npm install
   # or
   yarn install

3. Run the Development Server:

   npm run dev

   The web interface will be available at http://localhost:3000.

---

📖 API Usage Overview

The Backend exposes several key endpoints for the Saga workflow:

• POST /api/workflow/start: Initialize a new game generation session.
  • Accepts topic, research_required, etc.
• POST /api/workflow/feedback: Provide user feedback on the current stage (e.g., critique the generated Factions).
• POST /api/workflow/continue: Proceed to the next stage after approval.
• GET /api/workflow/state/{session_id}: Retrieve current generation state and data.
• POST /api/generate: Standalone endpoint for asset generation (images/3D).

---

📂 Project Structure

ProjectX/
├── backend/
│   ├── SagaAgent/         # Core logic for narrative generation (LangGraph)
│   ├── Research/          # Web research agent modules
│   ├── models/            # Pydantic data models
│   ├── nodes/             # Processing nodes for image/3D generation
│   ├── main.py            # FastAPI entry point
│   └── requirements.txt   # Python dependencies
├── web/
│   ├── src/
│   │   ├── app/           # Next.js App Router pages
│   │   └── components/    # React UI components
│   ├── package.json       # JS dependencies
│   └── next.config.ts     # Next.js config
├── generated_images/      # Output directory for visual assets
└── README.md              # Project documentation

📜 License

Project X - Internal Use Only