🛡️ Build a lightweight Intrusion Detection System for Linux with Suricata, offering real-time monitoring, customizable rules, and Python analysis for enhanced security.

🔬 Implementation of agent coordination architectures and scaling principles from 'Towards a Science of Scaling Agent Systems' (arXiv:2512.08296). Research-backed multi-agent framework with benchmarks and validation.

Computes CShM (shape measures) and other geometric indices from crystallographic information files (CIFs), which may contain single or multiple entries, or from COD (Crystallography Open Database) entries.

A research-grade Python implementation of decentralized multi-agent coordination using auction-based task allocation, designed for autonomous robotics and AI studies.

VINCE is the Vulnerability Information and Coordination Environment developed and used by the CERT Coordination Center to improve coordinated vulnerability disclosure. VINCE is a Python-based web platform.

Code for the paper "Learning a Decentralized Medium Access Control Protocol for Shared Message Transmission"

Academic research prototypes demonstrating multi-agent coordination theory without exposing production systems

Executable contracts for multi-agent AI coordination. Write contracts once in AL, transpile to Python/JavaScript/Go/Rust/C#. CrewAI, LangGraph, and AutoGen agents execute identical logic—deterministic behavior guaranteed. Production-ready Python (67/67 tests), 134/134 stdlib tests passing.

Multi-model federation module for Bonsai/BlenderBIM. Preprocesses IFC files to SQLite spatial index for sub-second queries across 100K+ elements. Generic utility for coordination, clash detection, routing, and reporting workflows.

[NIPS2025] A decentralized, RAG-enhanced multi-agent framework for LLMs with dynamic task routing and agent evolution.

Multi-agent reinforcement learning research platform with Apple Silicon optimization. Develop intelligent agents for coordinated task completion using PPO and neural architectures.

Fast Python implementation of KSUID (K-Sortable Globally Unique IDs) using Cython

Deep reinforcement learning system for coordinating autonomous drones in wildfire suppression. Custom NumPy-based Deep Q-Network achieves superior performance in emergency response simulation scenarios.

Master thesis project that simulates robot swarms for learning communication-aware coordination. @USI19/20.

[IEEE ICUAS 2022] Python scripts for swarming, formation control, and observer-based adversary detection for multi-UAVs (Tello Drones)

Calculates the geometry indices tau_4, tau_5 and O and shape measures (CShM) from crystallographic information file (CIF)

Universal Probabilistic Daily Reminder Coordination System for Anything

An open, minimalist Gymnasium environment for autonomous coordination in wireless mobile networks.

A pure-Python KSUID implementation

Model-based AI approach for network and service coordination leveraging uncertain traffic forecasts