AI Rank
← Open Source
buaacyw

code-world-model

Code World Model Official Repo

ModelsVision modelsPython
Open on GitHub
Momentum
+7stars in 24 hours+1.4%
503
Stars
20
Forks
—
This week
1
Contributors
Created 2026-08-26 · Updated 2026-10-14 · #1871 today
Top developers
buaacyw
README

Code World Model:
Coding Agent as World Brain

Yiwen Chen1,2   ·   Guosheng Lin2   ·   Chi Zhang1

1 AGI Lab, Westlake University      2 Nanyang Technological University

Project Page   |   arXiv

https://github.com/user-attachments/assets/4c13c5fb-ab45-4a0e-9e59-b85499ef7390

Quick start

  1. Follow the environment and installation guide.
  2. From the repository root, download the public CWM LoRA and deterministically expand the 40 compact Hugging Face examples:
./scripts/install_release_assets.sh "$PWD/release"
  1. Enter the prepared release directory and run a released configuration without changing its inputs, prompts, or seed:
cd release
CONFIG=examples/example_01/config.json
python -m cwm_h3_inference validate --config "$CONFIG"
CUDA_VISIBLE_DEVICES=0 python -m cwm_h3_inference prepare --config "$CONFIG"
CUDA_VISIBLE_DEVICES=0 python -m cwm_h3_inference generate --config "$CONFIG"

Use a new cache directory and output path for every changed experiment. The Hugging Face examples contain compact NPZ conditions, not caches or output videos; the installation script performs the required local format expansion.

Documentation