Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A platform for reproducible world model research and evaluation
| Date | Stars |
|---|---|
| 2026-07-24 | 2067 |
| 2026-07-25 | 2070 |
| 2026-07-28 | 2070 |
| 2026-07-30 | 2070 |
| 2026-08-06 | 2070 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
25.0
growth rate 0.00%/day
<h1 align="center">stable-worldmodel</h1>
<p align="center"><i>A platform for reproducible world model research and evaluation.</i></p>
<p align="center">
<a href="https://galilai-group.github.io/stable-worldmodel/"><img alt="Documentation" src="https://img.shields.io/badge/Docs-blue.svg"/></a>
<a href="https://github.com/galilai-group/stable-worldmodel"><img alt="Tests" src="https://img.shields.io/github/actions/workflow/status/galilai-group/stable-worldmodel/tests.yaml?label=Tests"/></a>
<a href="https://pypi.python.org/pypi/stable-worldmodel/#history"><img alt="PyPI" src="https://img.shields.io/pypi/v/stable-worldmodel.svg"/></a>
<a href="https://arxiv.org/abs/2605.21800v1" target="_blank" style="margin: 2px;"><img alt="ArXiv" src="https://img.shields.io/badge/arXiv-2605.21800-b5212f?logo=arxiv" style="display: inline-block; vertical-align: middle;"/></a>
<a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"/></a>
<a href="https://github.com/astral-sh/ruff"><img alt="Ruff" src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json"/></a>
<a href="https://colab.research.google.com/github/galilai-group/stable-worldmodel/blob/main/scripts/notebooks/train_from_hf_buckets.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"/></a>
</p>
<p align="center">
<a href="#installation"><b>Installation</b></a> ·
<a href="#quick-start"><b>Quick Start</b></a> ·
<a href="#environments"><b>Environments</b></a> ·
<a href="#solvers-and-baselines"><b>Solvers & Baselines</b></a> ·
<a href="https://galilai-group.github.io/stable-worldmodel/"><b>Documentation</b></a> ·
<a href="https://arxiv.org/abs/2605.21800v1"><b>Paper</b></a> ·
<a href="#citation"><b>Citation</b></a>
</p>
---
`stable-worldmodel` provides a single, unified interface for the three stages of world model research — **collecting data**, **training**, and **evaluating with model-predictive control** — across a large suite of standardized environments. It ships with reference implementations of common baselines and planning solvers so research code can stay focused on the contribution that matters: the model and the objective.
## Installation
From PyPI:
```bash
pip install stable-worldmodel # base only
pip install 'stable-worldmodel[all]' # + training, environments, and data formats
```
LeRobot dataset support is a separate opt-in extra (requires Python 3.12+): `pip install 'stable-worldmodel[lerobot]'`.
From source (development):
```bash
git clone https://github.com/galilai-group/stable-worldmodel
cd stable-worldmodel
uv venv --python=3.10 && source .venv/bin/activate
uv sync --extra all --group dev
```
Datasets and checkpoints are stored under `$STABLEWM_HOME` (defaults to `~/.stable_worldmodel/`). Override the variable to point at your preferred storage location.
> The library is in active development. APIs may change between minor versions.
## Quick Start
```python
import stable_worldmodel as swm
from stable_worldmodel.policy import WorldModelPolicy, PlanConfig
from stable_worldmodel.solver import CEMSolver
# 1. Collect a dataset
world = swm.World("swm/PushT-v1", num_envs=8)
world.set_policy(your_expert_policy)
world.collect("data/pusht_demo.lance", episodes=100, seed=0)
# 2. Load it and train your world model (format is autodetected)
dataset = swm.data.load_dataset("data/pusht_demo.lance", num_steps=16)
world_model = ... # your model
# 3. Evaluate with model-predictive control
solver = CEMSolver(model=world_model, num_samples=300)
policy = WorldModelPolicy(
solver=solver,
config=PlanConfig(horizon=10, receding_horizon=5),
)
world.set_policy(policy)
results = world.evaluate(episodes=50)
print(f"Success Rate: {results['success_rate']:.1f}%")
```
Reference implementations are provided in [`scripts/train/`](scripts/train):Excerpt of 16,019 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:25558afea385da64, topic:deep-learning, topic:pytorch
