All Projects

Memetic Agents

01-Mar-2025

A novel framework for creating AI agents capable of social learning and knowledge evolution through memetic principles, featuring multi-tiered memory architecture and inter-agent communication for persistent knowledge development.

Abstract The Memetic Agents Project represents a novel framework for creating AI agents capable of social learning and knowledge evolution. The system implements a multi-tiered memory architecture, dynamic prompt modification, and inter-agent communication protocols that enable agents to learn from experience and share knowledge. The framework demonstrates how AI agents can maintain persistent knowledge, engage in meaningful interactions, and evolve their capabilities through social learning mechanisms inspired by memetic theory.

Adaptive Multi-Agent System (ADAM)

01-Oct-2024

An adaptive multi-agent system that orchestrates a diverse set of specialized agents to deliver nuanced, accurate, and contextually-aware responses.

Project Overview ADAM is a sophisticated AI orchestration platform that leverages multiple specialized AI agents working in concert to deliver nuanced, accurate, and contextually-aware responses. The system demonstrates advanced capabilities in natural language processing, multi-agent coordination, and adaptive response generation.

B.A.A Black Sheep - Business Analysis Agent

28-Jun-2024

An early project developing an agentic workflow specialized in business analysis and process mapping.

Lessons in Agentic Workflow Design Introduction BAA Black Sheep was an early experiment of a large scale agentic workflow using LangGraph. The project served as a testing ground for exploring LLM capabilities and agentic pattterns in a realistic use case. There are severak flaws in its design, to be discussed later, but ultimately it was shelved to make way for newer projects as the world of LLMs and Agents has rapidly evolved.

Semantic File Crawler

28-Jun-2024

An AI-powered document management system that automatically organizes and creates meaningful connections between digital assets using knowledge graphs and natural language processing.

Introduction