// Projects

Some of our work.

20+ years of combined engineering experience applied to defence-adjacent AI, embedded OS, simulation systems, agentic automation, and secure networking.

//

// FEATURED

Aegis: Counter-UAS Interception & Drone Defence System

Aegis: Counter-UAS Interception & Drone Defence System

Commercially available drones weaponised as precision strike platforms, coordinated swarms, and loitering munitions have compressed detection-to-response windows to seconds. Legacy perimeter defence — built for fixed-wing aircraft and ballistic threats — cannot reliably acquire low-RCS, low-altitude UAS targets. Manual engagement chains collapse under swarm pressure. The operational gap is a threat layer growing faster than countermeasures adapt.

Computer VisionRF DetectionEdge AI

Perimeter Intelligence Suite: AI-Driven Border Surveillance

Perimeter Intelligence Suite: AI-Driven Border Surveillance

Existing perimeter security systems at critical infrastructure and border installations rely on static sensor networks and manual operator monitoring — creating detection latency and high false-positive rates that degrade operator trust and increase response times under real operational conditions.

Computer VisionEdge AISensor Fusion

AR/VR Training: Ship Engine Valve Maintenance & Repair

SimulationDefence

AR/VR Training: Ship Engine Valve Maintenance & Repair

Training maritime maintenance personnel on ship engine valve procedures requires access to live equipment — expensive, safety-constrained, and logistically difficult to schedule. Errors during training on live systems carry real risk of component damage.

CHAKRA-AI: Autonomous Agent Platform

AgentsEnterprise

CHAKRA-AI: Autonomous Agent Platform

Large organisations managing personnel across distributed locations rely on manual processes, Excel-based data shuttling, and disconnected record systems. Every assignment stage requires manual verification, offers no intelligent recommendations, and creates bottlenecks that compound across the organisation.

LangChainPythonLocal LLM

QA-INSPECTOR: Integrated Equipment Inspection Platform

EnterpriseDefence

QA-INSPECTOR: Integrated Equipment Inspection Platform

Equipment inspection in field environments relies on paper-based checklists, manual data entry into Excel, and periodic physical handoffs of records. There is no real-time visibility into inspection status, no automated compliance tracking, and no way for leadership to view workforce productivity or overdue inspections without chasing individual reports.

AndroidPythonSQLite

// MORE WORK

CaregiVR: VR Simulation Platform for Nurse Training

XR/SimulationHealthcare

CaregiVR: VR Simulation Platform for Nurse Training

Nurses performing manual patient transfers face high rates of musculoskeletal injury due to poor ergonomic technique. Practical training in Kinaesthetics-based transfer methods is limited to brief institutional courses, with no mechanism for self-directed practice or real-time feedback outside a supervised clinical setting.

Unity 3DC#SteamVR

EdgeCore OS: Lightweight Linux for IoT and Edge Compute

EdgeCore OS: Lightweight Linux for IoT and Edge Compute

Edge computing devices in industrial and IoT deployments require lightweight, highly configurable operating systems that can run on constrained hardware while supporting modern networking and sensor integration. General-purpose distributions carry too much overhead and expose unnecessary attack surface.

Immersive Industrial Training Platform

SimulationIndustrial

Immersive Industrial Training Platform

Industrial onboarding for complex equipment operation requires extended time on live equipment — expensive, safety-constrained, and difficult to repeat for refresher training. New operators cannot practice failure modes or emergency procedures safely in the real environment.

VRUnityIndustrial Training

AI Procurement Decision Support

AI Procurement Decision Support

Procurement analysts at complex organisations spend significant time manually correlating supplier data, compliance documentation, and historical performance across large, heterogeneous datasets. Analyst time is consumed by data retrieval rather than decision-making.

Compeer: Decentralised P2P Secure Messaging

NetworksDefence

Compeer: Decentralised P2P Secure Messaging

Centralised messaging infrastructure creates single points of failure, interception, and denial-of-service. Tactical and operational communication systems that must function in contested or denied network environments cannot rely on central server availability.

P2PCryptographyGo

FreeBSD 802.11n Kernel Driver: Atheros USB Wireless

FreeBSD 802.11n Kernel Driver: Atheros USB Wireless

Atheros USB wireless chipsets lacked 802.11n support on FreeBSD, limiting deployment options for embedded systems relying on FreeBSD's security and stability properties. Kernel-level wireless driver work requires correctness guarantees that application-level development does not.

APEX-RTOS: Real-Time Operating System for Industrial Edge Controllers

Embedded OSIndustrial

APEX-RTOS: Real-Time Operating System for Industrial Edge Controllers

Industrial automation controllers require deterministic, sub-millisecond interrupt response that general-purpose operating systems cannot guarantee. Commercial RTOS options restrict hardware targets and offer no recourse when scheduling guarantees fall short of specific latency requirements.

SecureLink: Protocol-Hardened Data Gateway for Multi-Site Operations

NetworksDefence

SecureLink: Protocol-Hardened Data Gateway for Multi-Site Operations

Operational systems spanning multiple physical sites need reliable, low-latency data routing with structured failover — without relying on external cloud infrastructure. Standard application-layer solutions introduce dependencies incompatible with security and availability requirements.

SYNAPSE: Distributed Consensus Engine for Multi-Node Command Systems

NetworksInfrastructure

SYNAPSE: Distributed Consensus Engine for Multi-Node Command Systems

Command systems with multiple processing nodes require consistent shared state even when individual nodes fail or network partitions occur. Centralised coordination creates single points of failure unacceptable in operational environments.

Distributed SystemsRaftGo

VECTOR: Parallel Processing Engine for Real-Time Multi-Sensor Fusion

VECTOR: Parallel Processing Engine for Real-Time Multi-Sensor Fusion

Real-time fusion of high-bandwidth data streams from multiple sensors exceeds single-node processing capacity at operational sample rates. General-purpose distributed computing frameworks introduce coordination overhead incompatible with latency requirements for operational use.