flowersteam/LLM-Culture
Code for the "Cultural evolution in populations of Large Language Models" paper
This tool helps researchers in fields like sociology, linguistics, or digital humanities study how stories and linguistic content change over time within a social network. You define a network of 'agents' (simulated individuals), give them personalities and initial stories, and then observe how their narratives evolve as they exchange and adapt stories from their 'neighbors.' The output includes metrics and visualizations that show changes in story similarity, keywords, and even sentiment across generations.
Use this if you want to simulate and analyze the cultural evolution of text-based content within a controlled population of AI agents, observing how narratives are transmitted and transformed.
Not ideal if you're looking for a tool to analyze existing human cultural data directly, rather than simulating hypothetical scenarios with AI models.
Stars
34
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/flowersteam/LLM-Culture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
CLAIRE-Labo/EvoTune
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
scientific-discovery/LLEMA
[ICLR 2026] LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery
OpenMLRL/LLM_Collab_Code_Generation
LLM Collaboration for Code Generation
papachristoumarios/llm-network-formation
Supplementary Code and Data for "Network Formation and Dynamics among Multi-LLMs"
chirindaopensource/bias_adjusted_LLM_agents_human_like_decision_making
End-to-End Python framework implementing bias-adjusted LLM agents for human-like decision-making...