Projects
Research artifacts, prototypes, and technical projects connected to AI, software engineering, autonomous systems, and self-adaptation.
Aware is a minimal Assess prototype for telemetry-based root-cause analysis. It combines a Parser agent, an Executor agent, and dynamic analysis sub-agents to turn an incident question into a validated BuildSpec and an execution report.
AgentLantern is a CLI devtool for multi-agent AI systems. It detects the framework, documents and lints the architecture, inspects the project model, and provides a live animated playground with saved-run replay and comparison capabilities.
GEAR separates the conceptual design of a multi-agent system from its execution framework. It uses feature-model-based specifications to model agents, workflows, constraints, and variation points, then generates framework-specific configurations and executable code from the same portable design.
An ongoing research project studying how to observe and measure the energy consumption of multi-agent AI systems across different execution and infrastructure configurations.
Learnix is a free and open learning platform for Python, data science, and machine learning. It combines structured learning paths, accessible courses, and practical notebooks so learners can understand concepts and immediately apply them.