World Models Python Packages

dreamer4

Implementation of Danijar's latest iteration for his Dreamer line of work

causal-worlds

Generate fictional-but-coherent causal operations worlds (executable sim + time-series + ground-truth causal answer-key) from a natural-language description — for benchmarking causal-discovery and control agents.

improving-transformers-world-model

Implementation of the new SOTA for model based RL, from the paper "Improving Transformer World Models for Data-Efficient RL", in Pytorch

x-transformers-rl

Implementation of a transformer for reinforcement learning using `x-transformers`

trio-retina

Model-agnostic state layer for world models — turn any detector (YOLO · VLM · DINO) into one standard, queryable stream of events + latent state. numpy-only, runs on CPU at the edge.

gaia2-pytorch

Implementation of the world model architecture for self driving out of Wayve

genie2-pytorch

Implementation of a framework for Genie2 in Pytorch

grilly

GPU-accelerated neural network operations using Vulkan compute shaders.

dreamerv2

Mastering Atari with Discrete World Models

geno-lewm

An action-conditioned JEPA world model for DNA, built on top of Carbon.

dreamerv3

Mastering Diverse Domains through World Models

flashdreams

high-performance inference and serving library for interactive autoregressive video and world models

ewm-core

Observable trajectory infrastructure — trading domain reference implementation

gemla

GEMLA: Γ–EML–α Transport Architecture SDK

dreamer

Mastering Diverse Domains through World Models

worldforge-ai

Harness framework to build world model based workflows for physical AI systems.

mmlm

Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra

loci-stdb

4D spatiotemporal vector database middleware for AI world models

pixyzrl

Reinforcement Learning with Pixyz (PixyzRL)

worldflux

Unified Python interface for world models in reinforcement learning