Research-grade PII detection for Mac, Windows, and Mobile. Scale from individual research papers to enterprise-wide cloud APIs.
Available: English & Dutch | More languages coming soon
"Jane Doe lives at 123 Baker St and works at Apple."
"PERSON_1 lives at ADDRESS_1 and works at ORG_1."
Based on the peer-reviewed Textwash project (GPL-3.0). Auditable, transparent, and built by academic researchers.
Uses category probabilities to anonymise phrases based on linguistic context, not just simple keywords.
Designed for sensitive institutional data. No internet connection required for the desktop application.
Choose the setup that best fits your workflow – from a user-friendly desktop app to cloud APIs and the original open-source script.
All variants are built around the same research-grade anonymisation approach and evaluation framework.
Mac · Windows · iOS · Android
A user-friendly application that runs entirely on your devices. Import unstructured text data and export anonymised versions – without sending anything to external servers.
Supports English and Dutch (more languages to come); designed to be easy to use for non-technical users.
Cloud-based processing · Zapier-ready
Cloud API for integrating Textwash anonymisation into your own systems and workflows. Ideal for automated pipelines, web apps, and low-code tools such as Zapier.
Process text from forms, CRMs, or ticket systems before storage or analysis.
Browser-based batch processing
Use Textwash in a managed cloud environment. Upload datasets, configure entity types, and run anonymisation jobs directly from your browser.
Ideal for teams who need shared project dashboards and result logs.
Original script · No GUI
The original open-source Textwash project that Textwash Pro builds on. A script-based anonymisation tool without a graphical interface, intended for technical users who want direct access to the underlying code.
Includes the full anonymisation pipeline and evaluation materials under GPL-3.0.
Textwash Pro is built to support real-world anonymisation workflows in research, industry, and the public sector.
If your use case involves unstructured text and personal data, Textwash Pro is likely relevant. Not sure? Reach out at textwash-pro@jocapps.eu
Anonymise free-text fields that contain personal data before storing or sharing them:
Prepare research datasets for sharing while protecting participants’ identities:
Remove direct and indirect identifiers from sensitive case descriptions:
Anonymise qualitative feedback before sharing within teams or with external partners:
Remove PII from semi-structured logs before central storage or analysis:
Combine Textwash Pro with institutional policies for tailored anonymisation workflows.
For custom integrations or specific compliance questions, contact textwash-pro@jocapps.eu
Textwash Pro was designed to meet high standards for text anonymisation. The following principles guide its development.
The underlying anonymisation approach has been evaluated empirically. This includes tests of what the tool can and cannot do, as well as a motivated intruder test where humans attempt to re-identify persons in anonymised documents.
The Textwash Pro application does not require you to upload text data or use any remote API. You can disconnect from the internet and continue anonymising documents. This minimises leakage and reduces risks for sensitive data.
Textwash Pro is based on the open, research-driven Textwash project. The foundations can be inspected, tested, and extended by the community.
Personal information is complex and context-dependent. Textwash therefore does not rely on simple dictionary lookups. Instead, it uses a machine learning model that assigns category probabilities to phrases and anonymises them accordingly.
Even if you do not use Textwash Pro, we strongly encourage you to ask any tool provider for:
If a provider refuses to supply this, you should be skeptical.
You can always reach us at textwash-pro@jocapps.eu if you have questions about evaluation details.
Textwash Pro offers a graphical user interface (GUI) for anonymising text files – no command line required:
Textwash Pro is designed to be user-friendly and works well for both small and large text collections. It can take advantage of powerful hardware where available, but does not require any technical setup.
If you would like a short demo or have specific questions about your use case, we are happy to help.
Also the orignal open-source Textwash project includes detailed person descriptions and their anonymised counterparts. These examples illustrate how the underlying anonymisation behaves.
You can use these example files to understand how different entity types are treated, and as a starting point for your own evaluation.
Browse Textwash Free on GitHubTextwash can anonymise a rich set of entity types and can be restricted to a subset as needed.
This allows you to align anonymisation with legal and methodological requirements while preserving as much non-identifying information as possible.
By selecting only the entity types you need, you can tailor anonymisation to your context while keeping as much useful, non-identifying information as possible.
We are sure that Textwash Pro is useful for your work. But even if you choose another tool, we strongly encourage you to ask developers to provide at least:
If they refuse to provide this, you should be skeptical.
For research collaborations or questions about using Textwash Pro in studies, please contact textwash-pro@jocapps.eu
We searched for tools that are as transparent, open in their foundations, and data-averse (in the sense of not unnecessarily collecting data) as Textwash. We did not find any.
If you have a tool that meets these requirements, we would be glad to promote it and list it here. If you think your tool is better, we would love to see your evaluation results – you can use all the data we used, and we are happy to assist with setting up a human intruder evaluation.
Reach out via textwash-pro@jocapps.eu if you would like to discuss interoperability or joint evaluations.
Textwash Pro is developed and distributed by Dr. Bennett Kleinberg & jocapps® GmbH and is based on Textwash (github.com/ben-aaron188/textwash) under the GNU General Public License v3.0. The original Textwash project was developed by Dr. Maximilian Mozes and Dr. Bennett Kleinberg.
Textwash Pro extends this foundation with a multi-platform GUI, deployment options, and additional tooling while preserving the open, research-driven ethos of the original project.