AISmithLab/CoBRA
[🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments
This toolkit helps social scientists and AI researchers precisely control the behavior of AI agents in simulations. It takes an AI model and a desired level of a specific cognitive bias (like the Framing Effect or Authority Effect) and adjusts the AI's responses. The output is an AI agent that consistently exhibits the specified behavioral bias, grounded in classic social science experiments.
Use this if you need to simulate human-like decision-making with specific, measurable cognitive biases in AI agents for research or experimentation.
Not ideal if you're looking to eliminate all biases from an AI agent or if your primary goal is general AI development rather than social simulation.
Stars
65
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/AISmithLab/CoBRA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/concordia
A library for generative social simulation
Mai-xiyu/Minecraft_AI
AI Play Minecraft
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...