Simulate human behavior with mass LLMs

🔗 Demo Video   •   🐦 Twitter

LlamaSim:

LlamaSim is a multi-LLM framework that aims to simulate human behavior at scale. Given a specific environment (e.g., voters in Pennsylvania, students at CMU), we replicate target groups, and aim to provide actionable insights for important questions/events.

More to come...

Roadmap

• Predictive Functionality
• Gradio Frontend (Local Demo)
• Agentic Functionality
• Demographically Aligned Agents
• Long-Term Memory (maybe mem0.ai?)
• Graph Theory Approach
• Live Data Feeds for Agents (allowing them to stay up-to-date)
• Live Demo

Usage:

git clone https://github.com/jw-source/LlamaSim

mv env.txt .env
#create venv
python3 -m venv .venv

#set the venv
source .venv/bin/activate

# install dependancies
pip install -r requirements.txt
cd src/run.py

from network import Network
agent_network = Network(population="Pennsylvania Voters", num_agents=5, max_context_size=4000)
prompt = "Gas prices are an all-time high."
question = "Are you voting for Kamala Harris?"
agent_network.group_chat(prompt, "random", max_rounds=1)
agent_network.predict(prompt, question)