Research-grade PII detection for Mac, Windows, Linux, and Mobile. Scale from individual research papers to enterprise-wide cloud APIs.
Available for texts in English, Dutch, French, Spanish, German, Italian & many more
"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 · Linux · 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, Dutch, French, Spanish, German, Italian, and many more; 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 cloud environment hosted by us or in your own organisation's cloud. 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 [email protected]
Anonymise free-text fields that contain personal data before storing or sharing them:
Keep long-term text repositories usable while reducing privacy risk before archival storage:
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:
Route prompts and free-text inputs through anonymisation before they reach external or internal LLM systems:
We design end-to-end anonymisation workflows that align with institutional governance, legal obligations, and research quality standards.
📋 Governance alignment
Policy mapping, retention definitions, and approval checkpoints for every data flow stage
🛡️ Controlled processing
Role-based access setup, secure review loops, and privacy controls for internal and external teams
📈 Audit readiness
Documented procedures, quality evidence, and repeatable validation protocols for compliance reviews
For institutional rollouts, integration planning, or compliance questions, contact [email protected]
Textwash Pro works as a standalone product. If helpful, we additionally offer optional implementation and consultancy support for research teams, companies, and public-sector organisations.
The optional service package combines operational design, integration planning, and quality assurance for sensitive text workflows.
Optional services are available for SMEs, enterprise teams, universities, healthcare, and public sector
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 this level of transparency is not available, treat risk claims with caution
You can always reach us at [email protected] if you have questions about evaluation details.
European Data Laws (GDPR)
Textwash Pro is 100% ready for current EU privacy requirements and aligns with GDPR principles, especially data minimisation, purpose limitation, and privacy by design/default (Articles 5 and 25 GDPR).
European AI Sovereignty
The Windows/Linux/macOS app runs fully local, offline, and air-gapped. No data leaves the client environment, and no external APIs are required.
Common questions about deployment models, support levels, and governance requirements
Yes. The product is fully usable on its own, and services are optional
Yes. We can define service levels, support windows, response targets, and escalation paths for qualifying organisations
Yes. We support public sector, research, healthcare, and regulated environments with governance-aligned implementation plans
Yes. Hybrid architectures can combine local processing with API or cloud components, depending on policy and risk constraints
We provide documentation inputs, quality checkpoints, and implementation evidence to help internal governance and external audits
Programme managers, data protection teams, and technical leads can contact us at [email protected] to discuss fit and rollout options
Textwash Pro is aligned with GDPR principles including data minimisation, purpose limitation, and privacy by design/default (Articles 5 and 25), and supports compliance-focused workflows for sensitive text handling.
Yes. The Windows/Linux/macOS deployment runs fully local and offline, so no data leaves the client environment and no external API connectivity is required.
Textwash Pro offers a graphical user interface (GUI) for anonymising text files with 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 original 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.
Textwash Pro is a commercial product built on a research-driven and openly documented foundation. For procurement and governance processes, we recommend reviewing independent evidence alongside product claims.
These materials help organisations make informed, auditable decisions about deployment readiness.
🛡️ Privacy in benchmark comparisons
Independent benchmark work compares Textwash against multiple anonymisation approaches and indicates that base Textwash is highly competitive and dependable on privacy performance
⚖️ Trade-offs over single-metric claims
Published studies discuss utility/privacy trade-offs (e.g., BLEU, re-identification risk, and computation cost), supporting practical model selection for real deployment constraints
📚 Evidence across publications
The evidence base spans peer-reviewed journals and conference proceedings, which support procurement, requirement governance, and internal documentation needs
• arXiv (2026): arxiv.org/pdf/2602.12806
• Nature Scientific Reports: nature.com/articles/s41598-023-42977-3
• Procedia Computer Science: sciencedirect.com/science/article/pii/S1877050925008518
• arXiv (2024): arxiv.org/abs/2411.05978
• ACM Digital Library: dl.acm.org/doi/abs/10.1145/3576050.3576070
• arXiv (2021): arxiv.org/abs/2103.09263
• and many more
For research collaborations, interoperability discussions, or evaluation questions, contact
[email protected]
Looking for an anonymisation partner for your product, organization, or research project? Let’s discuss integrations, pilots, and custom deployment options.
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.