Personal Health Insights Agent (PHIA)

A framework for building multi-agent AI systems. Enables LLMs to collaborate through hierarchical organization, parallel task execution, and extensible tools.

Deterministic, lightweight behaviour trees for C#. JSON & DSL support. Built for game AI, real-time agents, and rapid iteration.

Open-source failure intelligence platform for LLM & agent systems. Adds failure memory, pre-flight warnings, pattern detection, and system health scoring.

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

An open, neutral protocol for generating standardized intent metadata across apps, agents, and AI systems.

Lightweight Agent Framework for building AI apps with any LLM

This repo contains the original JADE code from the SVN of Telecom Italia

Immutable constraint kernel with cryptographic genesis anchored on the XRP Ledger.

📈 Experiment with LLM-assisted equity trading flows in a modular sandbox using MCP servers, trader agents, and a simple SQLite database for accounts.

Eine Verbindung aus Agentensystemen, Evolutionären Algorithmen und Kapitalismus

Small multi-agent program to analyze features of python based MAS frameworks.

Semester project for Intelligent Software - Bots for Unreal Tournament

A model multi-agent config for agentic code-gen with an educational "loop"

TraceIQ is a Python library for measuring, analyzing, and auditing AI-to-AI influence in multi-agent systems, providing reproducible metrics for semantic drift, influence propagation, and cascade risk to support safe, transparent, and scientifically grounded agent collaboration.

A systems-first implementation of agent control: explicit retrieval decisions, planner–executor separation, and auditable memory as core architectural mechanisms.

Constrained Observation Lab: two small Vite+TypeScript demos (2D + 3D) showing how limited “slice” measurements drive prediction, drift detection, and correction. Includes Paper 1 backing artifacts (pre/post bundle) and 3D A/B mirrored traces. CC BY-NC 4.0.

A production-grade quality gate for agent systems. 9 parallel critics. Evidence-grounded. Learning memory.

This course is designed to teach you how to QUICKLY harness the power of the LangChain library for LLM applications. Build 3 end-to-end working LangChain based generative AI applications with no fluff, no toy examples - just real projects using real APIs and real-world skills.

Equity-Traders is an AI-powered trading assistant built using MCP servers and the OpenAI SDK. It simulates intelligent equity trading workflows, enabling market analysis, trade execution logic, and decision-making support for financial strategies.