Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture

Mathematical benchmark exposing the massive performance gap between real agents and LLM wrappers. Rigorous multi-dimensional evaluation with statistical validation (95% CI, Cohen's h) and reproducible methodology. Separates architectural theater from real systems through stress testing, network resilience, and failure analysis.

A Personal AI Assistant that lives inside your machine and works 24/7 for you.

🎙️ Voice-native document intelligence using Gemini, ElevenLabs STT/TTS, and Datadog observability — turning text documents into spoken conversations.

A Recursive Ontological Framework for Cognitive Design, Neurodivergence Modeling, AI Co-Development, and "Structural AI"

Technical Research: System prompts as governance constitutions for AI developer assistants.

A minimal kernel for agentic systems. Runtime-first architecture for programmatic tool execution. Inspired by Anthropic's Code Execution with MCP.

Embodied agent that learns from human teaching; hybrid agent architecture with computer vision, AI planning, knowledge graph reasoning & generalization , inverse kinematics. Supported by the DARPA GAILA program.

Case Study of the laboratory plant myJoghurt - implemented with JaCaMo BDI agents embedding an engine for processing the NPL(s) language and a set of capabilities for approaching the sanctioning norm enforcement process

Comprehensive cognitive infrastructure for AI-augmented development and knowledge work

A lightweight, pluggable memory backend for agent-based simulations. Supports temporal data, experience replay, and persistent state logging

First domain agent in A2A architecture. Family life management with JSON-RPC 2.0 agent-to-agent protocol.

An open-source engineering blueprint for defining and designing the core capabilities, boundaries, and ethics of any AI agent.

Michael Lorenz, M.Sc. Energy & Environment Technology (KIT) – Strategic AI Engineer, Cognitive Technologist & Digital Strategist

Real-world patterns for shipping AI agents to production. Learn versioning, cost optimization, multi-tenancy, guardrails, and observability through runnable TypeScript examples.

Multi-Agent Kubernetes Cost Optimization System

🤖 Benchmark AI agent capabilities, bridging the gap between hype and reality with clear metrics and insights for informed development decisions.

AutoMCP: Dynamic Tool Synthesis via Code Pattern Mining and Self-Regenerative Agent Architectures

A minimal framework for evaluating agentic AI architectures. Includes evaluation templates, scoring guide, and case studies (LangChain, AutoGen, CrewAI). Most agent failures trace to state management, not reasoning.