pysociety 0.2.0

Multi-agent society simulation with playful personalities

A Society of Agents

Inspired by Marvin Minsky's Society of Mind, a multi-agent simulation where AI personalities debate questions from different perspectives. Ask a question, specify the viewpoints you want, and watch the debate unfold.

What it does

1. You provide a question and the perspectives you want represented
2. AI generates distinct agent personalities for each perspective
3. An orchestrator facilitates debate between the agents
4. Agents discuss, disagree, and build on each other's arguments

Quick Start

Setup

1. Clone the repository
2. Create a .env file with your API key:

ANTHROPIC_API_KEY=your-api-key-here

3. Install dependencies:

uv sync

Run a debate

uv run python -m llm_society "What is the meaning of life? I want an optimistic view and a pessimistic one."

More examples

# Ethics debate
uv run python -m llm_society "$(cat examples/trolley_problem.txt)"

# Philosophy
uv run python -m llm_society "$(cat examples/free_will.txt)"

# Social issues
uv run python -m llm_society "$(cat examples/wealth_inequality.txt)"

Example Questions

File	Topic	Perspectives
meaning_of_life.txt	Meaning of life	Optimist, Pessimist
trolley_problem.txt	Trolley problem	Utilitarian, Deontologist, Virtue ethicist
free_will.txt	Free will	Determinist, Libertarian, Compatibilist
wealth_inequality.txt	Wealth inequality	Libertarian, Socialist, Rawlsian, Communitarian
animal_rights.txt	Animal rights	Peter Singer, Traditionalist, Environmental ethicist
civil_disobedience.txt	Civil disobedience	Thoreau, MLK, Legal positivist, Conservative

Optional Configuration

You can customize models in .env:

# Main orchestrator model
MAIN_AGENT_MODEL=anthropic:claude-opus-4-5-20251101

# Sub-agent models
SUB_AGENT_MODEL=anthropic:claude-sonnet-4-5-20250929

# Prompt generation model
PROMPT_GENERATOR_MODEL=anthropic/claude-opus-4-5-20251101