Princeton-AI2-Lab/Web-World-Models

Official Project Page for Web World Models (https://arxiv.org/abs/2512.23676)

48
/ 100
Emerging

This project helps AI developers build persistent, interactive digital worlds for language agents. It allows for the creation of environments with consistent rules and physics, while still enabling large language models to generate dynamic content, narratives, and high-level decisions. The end-user persona is an AI researcher or developer working on language agents or simulated environments.

Use this if you need to create a stable, rule-bound digital world for language agents, where the environment's core logic is consistent, but narratives and high-level interactions are driven by large language models.

Not ideal if you need a fully generative world where every aspect, including fundamental physics and state, is imagined by a model, or if you're building a traditional web application without AI agent interaction.

AI agent development simulated environments large language models virtual world creation interactive AI systems
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 13 / 25
Community 16 / 25

How are scores calculated?

Stars

87

Forks

14

Language

TypeScript

License

CC-BY-4.0

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Princeton-AI2-Lab/Web-World-Models"

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