Github Repositories Related to ComStock
These repositories are publicly available for use, but we are not able to provide technical support or documentation for running ComStock at this time. We strongly suggest and support using the public datasets. The dataset outputs from the initial ComStock (V1.0) release can be found by visiting Published Datasets page.
ComStock Repository
This repository contains the source code used to build and execute ComStock models, including upgrade scenarios. In addition, the sampling of building characteristics used for the initial ComStock (V1.0) release is provided. The ComStock model is under active calibration and development, which is publicly visible on this repository.
OpenStudio-Standards Repository
ComStock relies heavily on openstudio-standards, a Ruby Gem library that extends the OpenStudio SDK. It has four main use-cases:
- Provide higher level methods to help BEM users and developers to create OpenStudio models from existing geometry, or programmatically generated geometry
- Create typical building models in OpenStudio format
- Create a code baseline model from a proposed model
- Check a model against a code/standard
OpenStudio-Standards Repository
Buildstock Batch Repository
Execution of the ComStock workflow is managed through the buildstockbatch repository, a shared asset of ResStock and ComStock, specifically developed to scale to execution of tens of millions of simulations through multiple infrastructure providers.
BuildStockQuery Repository
buildstock-query is a Python library for querying datasets generated by ResStock™ and ComStock™. Introductory tutorial videos can be found on the NLR Learning BuildStock Analysis YouTube channel.
BuildStock Corpus Repository
buildstock-corpus publishes ComStock’s documentation in an AI-ready form: clean Markdown for every page on this website, the reference documentation, and every upgrade measure report, organized by dataset release. Every file opens with a provenance header naming its source, publication status, and corpus release tag, so an LLM or agent can read and cite it directly without scraping this site. Each corpus build is tagged and tags never move, so a citation resolves to the same text later. Agents should start with the repository’s AGENTS.md, which explains how to read and cite the corpus, or with this site’s llms.txt.
Example Jupyter Notebooks
Helpful notebooks are posted to this page. We have also heard many folks have success with ChatGPT writing custom scripts.