Redaction API
Java
Philter
Turnkey, self-hosted PII redaction with a clean API. Drops into any pipeline that needs sensitive data removed from text — and runs entirely inside your cloud.
Community
Get involved with Philterd
Philterd is open source software for PII and PHI redaction. The toolkit, the issues, the conversations — all happen in public. Here’s how to participate.
Open source toolkit
10 Apache 2.0 projects under github.com/philterd — read the code, file issues, contribute pull requests.
Redaction Library
JavaPython.NETGo
Phileas
The core redaction, anonymization, masking, and replacement library underneath Philter. Available in Java, Python, .NET, and Go.
AI Models & Server
Python
PhEye
The trained AI and NLP models that find PII and PHI in text, plus the service that hosts them. Designed to plug directly into Phileas and Philter.
Discovery
Java
Phinder
High-speed discovery scanner that crawls files and storage to map where sensitive information actually lives across your environment.
Monitoring
Go
Phield
Intelligent monitoring that tracks PII flow across the organization and alerts on suspicious activity or unusual trends.
LLM proxy
Java
Philter AI Proxy
Drop-in proxy that redacts PII and PHI before prompts reach LLM providers like OpenAI and Anthropic Claude.
Benchmarking
Go
Philter Scope
Standalone audit tool that scores redaction policies on precision and recall, so policy changes can be measured rather than guessed at.
Human review
Java
Arbiter
Human-in-the-loop PII redaction. Search, review, and override automated detection decisions with structured exemption codes — built for AI training-data prep and regulated everyday workflows.
Differential privacy
Python
Philter Diffuse
Privacy-first analytics that applies differential privacy to PII counts, preserving statistical utility without exposing individuals.
Policy editor
JavaScript
Redaction Policy Editor
Web console that lets non-technical users build and deploy redaction rules through a visual, no-code interface.
Discussions & support
GitHub Discussions
Ask questions, share patterns, propose features. Discussions live alongside each repo’s issues — start at github.com/orgs/philterd/discussions.
Issues & bug reports
Found a bug? File it in the relevant repo’s issue tracker — we triage weekly. For security-sensitive reports, see SECURITY.md in any repo.
Commercial support
Need an SLA, a custom evaluation on your data, or hands-on engineering? Get in touch — we work directly with healthcare, finance, legal, and government teams.
Contributing
Pull requests welcome — bug fixes, new entity detectors, language support, docs improvements. Each repo has its own CONTRIBUTING.md.
Currently open: good first issues
Issues labeled good first issue across the philterd org.
No "good first issue" tickets are open right now — nice problem to have. Browse the repos directly for other ways to contribute, or open an issue with your idea.
Getting started
- Start with the contributor guide. Philter’s CONTRIBUTING.md sets the pattern; other repos follow it.
- Code of Conduct. We follow the Contributor Covenant. Be excellent to each other.
- License. All code is Apache License 2.0. Contributions are accepted under the same terms.
- Search across all repos: good first issues · help wanted
Recent releases
Each project ships independently. Per-repo release feeds:
- Philter — releases on GitHub →
- Phileas — releases on GitHub →
- PhEye — releases on GitHub →
- Phinder — releases on GitHub →
- Phield — releases on GitHub →
- Philter AI Proxy — releases on GitHub →
- Philter Scope — releases on GitHub →
- Arbiter — releases on GitHub →
- Philter Diffuse — releases on GitHub →
- Redaction Policy Editor — releases on GitHub →
Stay informed
Infrequent updates of technical posts and community highlights.
Maintainers
Philterd is built and maintained by Jeff Zemerick — PMC Chair of Apache OpenNLP and primary developer behind the entire toolkit. The contact form below reaches Jeff directly.