Key Features

• Basic flight dynamics model (FDM) and weapon systems simulation
• Custom game engine with OpenGL 4.5 and VR support
• Physically-based rendering with atmospheric scattering
• Missile guidance systems with launch envelope calculation
• Terrain system covering 500 x 500 km areas
• Custom avionics UI system

This is an experimental flight simulator that only scratches the surface of the complexity of modern aircraft simulation. Nevertheless, it's a rather complex piece of software that touches on all the major points of flight simulation with modern avionics.

RogueLLM allows players to request any kind of setting for the game to be generated. Locations, enemies, and items are all procedurally generated based on the theme requested. The theme can be as simple as a single word (e.g. "fantasy") or a detailed description up to 3,000 characters.

Key Features

• LLM integration for dynamic narrative and interactions
• Procedurally generated settings based on player requests
• Item and equipment systems
• Combat mechanics
• Inventory management

The game currently focuses on combat and inventory management mechanics while leveraging AI to create unique and personalized gaming experiences.

This project demonstrates a minimal neural network training infrastructure for simple simulations where controllers are involved. The AI is built using a neural network that is trained through genetic algorithms to perform obstacle avoidance in a self-driving scenario.

Key Features

• Neural network-driven self-driving AI with obstacle avoidance capabilities
• Neural Network training and inference in C++ with no external dependencies
• Real-time visualization of the simulation and training progress
• Minimal immediate-mode rendering API based on OpenGL