google-deepmind/concordia

A library for generative social simulation

68
/ 100
Established

This tool helps researchers, strategists, and analysts simulate complex social situations, like how people might react in a pub during a snowstorm or how different teams interact in a digital environment. You provide natural language descriptions of characters and settings, and it generates realistic interactions and outcomes based on those inputs. It's designed for anyone studying human behavior, testing AI safety, or evaluating service performance through simulated usage.

1,252 stars. Actively maintained with 8 commits in the last 30 days.

Use this if you need to understand or predict human-like behavior and interactions in various scenarios without conducting real-world experiments.

Not ideal if you're looking for a simple data analysis tool or don't have access to a large language model API.

social-science-research behavioral-simulation AI-safety-ethics synthetic-data-generation scenario-planning
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,252

Forks

291

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2026

Commits (30d)

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/google-deepmind/concordia"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.