← Discover
Discover · GitHub · stable-worldmodel↑ +319 today

Accelerate World Model Research

stable-worldmodel; It is a platform that ensures that research on 'world models' is repeatable and comparable. It particularly focuses on research and evaluation processes.

Updates

  • August 2, 2026: Stars 1,403 → 2,080, latest release 0.1.1 (June 6, 2026).

What does it do?

  • Making research reproducible.
  • Providing a standard assessment environment.
  • Not an end user tool, but a direct solution for research.

How to install, how to use?

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

Install stable-worldmodel in my Python environment with the command 'pip install stable-worldmodel[all]' and help me prepare a small script that collects data in a sample PushT environment and trains and evaluates a world model.

Install from PyPI (all plugins)
pip install 'stable-worldmodel[all]'
List cached datasets
swm datasets

Related dictionary terms

Open SourceArtificial Intelligence
Who it is forML/RL researchers
DifficultyAdvanced research-oriented
What offersReproducible world-model research platform
LicenseStandart tespit edilemedi · ayrıntı aşağıda
Feeopen source
License: GitHub did not detect a standard license. Check LICENSE on repo before reuse.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-05-30: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.