Skip to content

Course: From Conway to LangGraph - Agent Systems for Physicists`

License

Notifications You must be signed in to change notification settings

mirko-degli-esposti/Conway-to-LangGraph

Repository files navigation

From Conway to LangGraph

Agent Systems for Physicists in the LLM Era

Course Banner

A 48-hour Master's course bridging Cellular Automata and Modern AI Agents

License: CC BY-NC-SA 4.0 Python 3.10+ Code style: black Status


🎯 Course Overview

"How do simple local rules give rise to complex global behavior?"

This course explores emergence — from Conway's cellular automata (1970) to today's multi-agent LLM systems. Students learn to:

  • 🧮 Formalize emergence using statistical mechanics & information theory
  • 💻 Simulate agent systems from first principles (Python/Mesa)
  • 🤖 Build AI agents using foundation models (LangChain/LangGraph)
  • 🔬 Apply these tools to physics research problems

📚 Course Structure

12 weeks • 48 hours • Theory + Hands-on Labs

WeeksTopicKey ConceptsTools
1 Cellular Automata Emergence, Wolfram's classes NumPy, Matplotlib
2 Game of Life Emergence, Entropy and Irreversibility NumPy, Matplotlib
3-4 Statistical Mechanics of Agents Scelling Model,Phase transitions, Self organized ciritcality, mean-field theory Mesa, Python
5-6 RL & Evolutionary Learning Q-learning, MARL, genetic algorithms Gymnasium, NumPy
7-8 Foundation Models Transformers, prompting, tool use Ollama, OpenAI API
9-10 LangChain & LangGraph Chains, agents, memory, tools LangChain, ChromaDB
11-12 Multi-Agent Systems Coordination, collaboration, emergence LangGraph, AutoGen

🚀 Quick Start

Prerequisites

  • Background: Physics (statistical mechanics, dynamical systems)
  • Programming: Python intermediate (OOP, NumPy)

Installation (5 minutes)

# 1. Clone repository
git clone https://github.com/mirko-degli-esposti/conway-to-langgraph.git
cd conway-to-langgraph

# 2. Create environment
conda env create -f environment.yml
conda activate conway-langgraph

# 3. Verify setup
python scripts/verify_setup.py

# 4. Launch Jupyter
jupyter lab

📖 How to Use This Repository

For Students

  1. Each week:
    • Read weekXX_topic/README.md for overview
    • Complete Jupyter notebooks in notebooks/
    • Solve exercises in `exercises/

📅 Course Calendar

[https://www.unibo.it/en/study/course-units-transferable-skills-moocs/course-unit-catalogue/course-unit/2025/535121/orariolezioni]


📜 License


👨‍🏫 Instructor

Mirko Degli Esposti
[Full Prof. in Mathematical Physics, Department of Physics and Astronomy]
[University of Bologna]

Contact:

🗺️ Repository Navigation

📦 conway-to-langgraph/
 ┣ 📂 week01_elementary_ca/      ← Start here!
 ┣ 📂 week02_game_of_life/
 ┣ 📂 week03...../               ← Setup, bibliography, syllabus
 ┣ 📜 README.md                  ← You are here!

Ready to explore emergence from Conway to LangGraph? 🚀

Get Started →


Last updated: February 2026

About

Course: From Conway to LangGraph - Agent Systems for Physicists`

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors