galilai-group/stable-worldmodel

Health v2 · maintenance only

Adoption not part of the score

2260 stars · 288 forks observed · 2026-10-15

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library providing a unified platform for reproducible world model research, covering data collection, training, and evaluation via model-predictive control across standardized environments. It ships reference baselines and planning solvers so researchers can focus on their model and objective.

Use cases

• train and evaluate world models in standardized environments
• run model-predictive control planning baselines
• collect and store simulation datasets with Lance format
• benchmark JEPA-style world models reproducibly
• add custom environments and train world models on them
• embed planning solvers in robotics stacks

When to choose

• you need a unified pipeline for world model data collection, training, and MPC evaluation
• you want standardized environments and reference baselines instead of re-implementing them
• you need reproducible evaluation protocols for world model research

When to avoid

• you need a production agent framework rather than a research library
• you only need off-the-shelf pretrained world models without training
• you cannot install GPU/PyTorch dependencies

Facets

library · maturity active

machine-learning deep-learning simulation benchmarking etl machine-learning deep-learning reinforcement-learning robotics python cross-platform world-models jepa model-predictive-control pytorch reinforcement-learning evaluation-benchmarks lance-datasets planning-solvers research gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="galilai-group/stable-worldmodel")