ARCortex’s immersive AR/VR platform, originally built in Unity with multi-API integration, provided a modular foundation for geospatial, multi-user AR experiences. However, rapid advances in AI, no-code tools, and agent-based computing now enable a paradigm shift. This project aims to re-architect the platform from the ground up, leveraging new methods that drastically reduce human development effort while increasing creative flexibility, scalability, and runtime adaptability.

The redesign will explore:

• Model Context Protocol (MCP) and A2A protocol for agent coordination and composability
• No-code and low-code interfaces for rapid prototyping and domain expert use
• Computer-use agents for intelligent orchestration of world-building, asset generation, and behavior scripting
• On-the-fly world and video generation, using generative AI to create immersive environments and scenes without manual modeling
• Emerging physics AI models to simulate realistic interactions without manual tuning
• Evaluation of scene-based vs. video-based authoring workflows to optimize for performance and storytelling
• Adoption of dynamic runtime systems to load assets and behaviors based on context, reducing app size and increasing flexibility

Deliverables:

• Reimagined architecture design based on agents, generative AI, and modular execution
• Prototype implementation integrating no-code pipelines, AI-driven scene generation, and cloud/edge execution
• Evaluation report on scene-based vs. video-based experiences, including authoring time and user engagement metrics
• Demonstration system showing an end-to-end workflow: from high-level user prompt to deployed immersive AR/VR experience
• Security and performance audit to validate new architecture for real-world deployment
• MCP-compliant system design enabling distributed component management and AI-driven orchestration

Re-architected immersive platform leveraging Unity and/or alternative runtime environments, restructured to support dynamic module loading, OpenXR standardization, and composable runtime behaviors.

Integration of generative AI, LLMs, and ML agents to enable intelligent scene creation, behavior generation, world interpretation, and user intent translation through natural language or voice input.

MCP and A2A-compliant system architecture, supporting orchestration of computer-use agents for real-time scene management, modular feature injection, and autonomous tool coordination.

Cloud-based and edge-distributed processing pipeline that dynamically assigns workloads (e.g., scene generation, physics simulation, video rendering) to appropriate compute layers, including low-power devices.

Support for on-the-fly world and video generation, integrating generative 3D models, procedural storytelling, and upcoming physics AI models to simulate real-time environments with minimal manual authoring.

Next-gen no-code/low-code interface, empowering developers and domain experts to build multi-user, geo-referenced immersive experiences with minimal technical overhead—enabled by AI-driven prompts and reusable logic blocks.

Advanced security and deployment model, ensuring secure, scalable delivery of AR/VR experiences across varied devices and environments, including enterprise and defense settings.