Software produced for the BitCurator family of research projects (BitCurator, BitCurator Access, BitCurator NLP).

View My GitHub Profile

The BitCurator organization on GitHub houses the source code, documentation, and other supporting materials for the BitCurator (2011-2014), BitCurator Access (2014-2016), and the BitCurator NLP (2016-2018) projects.

Additional information replicated from the site:

BitCurator Environment

The BitCurator Environment is a Ubuntu-based Linux distribution designed to assist collections professionals with media imaging, forensic analysis, and reporting tasks when working with digital collections. It can be installed into a clean Ubuntu LTS release. Some releases can also be downloaded as a pre-built virtual appliance.

Download the latest stable release

Repository list:

Visit the README at to learn how to deploy BitCurator in a stock Ubuntu 22.04LTS or 20.04LTS OS.

Other BitCurator Research Software

The repositories listed below are end-of-life and no longer maintained.

BitCurator Access Webtools

The BitCurator Access Webtools project is comprised of a single repository. The README provides instructions for both end users and developers to clone and build from source.

BitCurator Access Redaction Tools

The BitCurator Access Redaction tools project is comprised of two repositories. The READMEs provide instructions for both end users and developers to clone and build from source.

BitCurator NLP Tools

The BitCurator NLP project includes several repositories. The topic model generation environment (bitcurator-nlp-gentm) enables automatic extraction of text from heterogeneous document collections within disk images to generate user-browsable topic models within a web browser. The disk browsing environment (bitcurator-access-webtools) provides full-text browsing of documents contained within disk images, along with (in progress) analysis of entities identified within those documents. Various command-line tools are provided in another repository (bitcurator-nlp-entspan).


BitCurator repositories are maintained by volunteers in the community. Interested in participating? Message the group, send a pull request, or send a note to the mailing list at