Code World Model:
Coding Agent as World Brain

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"

3. 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.

• Environment, installation, model, LoRA, and example downloads
• Input format, configuration, and inference
• License, project notice, and third-party notices