# Philterd > Philterd, LLC builds open source software for finding and redacting PII and PHI (personally identifiable and protected health information) in text and documents. Everything is self-hosted: it runs inside the customer's own cloud, servers, or desktop, so sensitive data does not go to a third-party API. The flagship, Philter, has been in production since 2019. Philterd sells cloud marketplace deployments, Philter Desktop licenses, support, and consulting around the open source toolkit. Key facts: - The toolkit is open source under the Apache License 2.0 and free to self-host. Source is at https://github.com/philterd. - Philter is a self-hosted REST API for PII and PHI redaction. Phileas is the redaction library underneath it, available for Java, Python, and .NET. - Detection combines pattern and checksum rules, dictionaries, and trained NLP models (PhEye). Detection is probabilistic, so redaction reduces how much sensitive data gets through rather than catching every instance. Customers are expected to validate output against their own data, and Philter Scope exists to measure precision and recall. - Redaction is driven by policies (JSON documents) that choose which entity types to find and what to do with each: redact, mask, replace with fake data, hash, encrypt, and so on. - Because the software runs in the customer's environment and Philterd never receives the data, Philterd is not a business associate and does not need to sign a BAA. The toolkit supports HIPAA, GDPR, CCPA, and similar compliance efforts but does not by itself make a system compliant. - Philterd is a small company founded and run by Jeff Zemerick, who writes the code and does the consulting work. Contact: hello@philterd.ai. ## Products - [Philter](https://philterd.ai/philter/index.md): 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. Docs: https://philterd.github.io/philter/ Source: https://github.com/philterd/philter - [Phileas](https://philterd.ai/phileas/index.md): The core redaction, pseudonymization, masking, and replacement library underneath Philter. Available in Java, Python, and .NET, with checksum-validated identifiers for national and financial IDs. Docs: https://philterd.github.io/phileas/ Source: https://github.com/philterd/phileas - [Philter Desktop](https://philterd.ai/philter-desktop/index.md): Offline Windows desktop app that redacts PII from PDF, Microsoft Word, Excel, text, and email files entirely on your own machine, using the same Phileas policy format as Philter. Source: https://github.com/philterd/PhilterDesktop - [PhEye (component)](https://philterd.ai/ph-eye/index.md): 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. Docs: https://philterd.github.io/ph-eye/ Source: https://github.com/philterd/ph-eye - [Phinder](https://philterd.ai/phinder/index.md): Discovery scanner that walks local files and directories to map where PII and PHI live, with a risk score for each file. Docs: https://philterd.github.io/phinder/ Source: https://github.com/philterd/phinder - [Phield](https://philterd.ai/phield/index.md): PII trend monitoring that tracks PII type counts across the organization and alerts when a count rises well above its baseline. Docs: https://philterd.github.io/phield/ Source: https://github.com/philterd/phield - [Philter AI Proxy](https://philterd.ai/philter-ai-proxy/index.md): Drop-in proxy that redacts PII and PHI before prompts reach LLM providers like OpenAI, Anthropic Claude, Gemini, and Bedrock. Docs: https://philterd.github.io/philter-ai-proxy/ Source: https://github.com/philterd/philter-ai-proxy - [Philter Scope](https://philterd.ai/philter-scope/index.md): Standalone audit tool that scores redaction policies on precision and recall, so policy changes can be measured rather than guessed at. Docs: https://philterd.github.io/philter-scope/ Source: https://github.com/philterd/philter-scope - [Philter Workspace](https://philterd.ai/philter-workspace/index.md): 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. Docs: https://philterd.github.io/philter-workspace/ Source: https://github.com/philterd/philter-workspace - [Philter Diffuse](https://philterd.ai/philter-diffuse/index.md): Applies differential privacy to PII counts, with a formal bound on what each release reveals about any one document. Docs: https://philterd.github.io/philter-diffuse/ Source: https://github.com/philterd/philter-diffuse - [Redaction Policy Editor](https://philterd.ai/redaction-policy-editor/index.md): Web console that lets non-technical users build, test, and download redaction policies through a visual, no-code interface. Docs: https://philterd.github.io/philterd-redaction-policy-editor/ Source: https://github.com/philterd/philterd-redaction-policy-editor - [PhiSQL (component)](https://philterd.ai/phisql/index.md): Declarative query language for PII operations. Write readable redaction policies as code that compile to the standard Phileas JSON schema. Docs: https://philterd.github.io/phisql/ Source: https://github.com/philterd/phisql - [Philter One](https://philterd.ai/philter-one/index.md): Philter One is a small office computer that redacts personal information from documents, coming soon for small businesses. Join the list for early access. ## Pricing and services - [Pricing](https://philterd.ai/pricing/index.md): The toolkit is open source and free. Philter runs on cloud marketplaces from $0.49 an hour, Philter Desktop is $199 per user per year, and consulting is quoted. - Philter: From $0.49 / hour. The turnkey, self-hosted PII redaction API, available for one-click deploy from the AWS, Google Cloud, and Azure marketplaces. Billed through your existing cloud account and running in your own cloud. - Philter Desktop: $199 / user / year. Offline PII redaction for Windows. Redacts PDF, Word, Excel, text, and email files entirely on your own computer. Free for personal and evaluation use; $199 per user per year for commercial use. - [Deploy Philter to the cloud](https://philterd.ai/philter/deploy/index.md): One-click deployment from the AWS, Google Cloud, and Azure marketplaces, billed through the customer's cloud account. - [PII Redaction Consulting](https://philterd.ai/consulting/index.md): Work directly with the creators of Philter. We assess what you need and deliver an implementation plan, then build it in your cloud or hand it to your team. - [PII Data Pipeline Consulting](https://philterd.ai/consulting/pii-data-pipelines/index.md): What a PII data pipeline engagement looks like. We design the redaction, build it inside your cloud, measure it on your data, and hand you a system you own. - [Know your app's PHI risk](https://philterd.ai/consulting/healthcare-app-phi-assessment/index.md): A read-only PHI risk assessment for healthcare apps. Findings with locations, a verdict you can show, and a plan to move to managed HIPAA hosting. - [AI Training-Data De-Identification Consulting](https://philterd.ai/consulting/ai-training-data-de-identification/index.md): What a typical AI training-data de-identification engagement with Philterd looks like: phases, deliverables, data handling, and how to start. - [Support](https://philterd.ai/support/index.md): Get help with Philter, Philter Desktop, and the Philterd toolkit: the knowledge base, product docs, issue trackers, commercial support, and security reports. ## Use cases by industry - [PII Redaction by Industry](https://philterd.ai/use-cases/index.md): Vertical PII redaction patterns for healthcare, finance, legal, insurance, government, education, contact centers, and AI, with the regulations that apply. - [PHI Redaction for Healthcare](https://philterd.ai/use-cases/healthcare/index.md): Redact PHI on a Windows PC with Philter Desktop, or in your own cloud with Philter. For hospitals, health systems, and medical and dental practices. - [PII Guardrails for AI and LLM Applications](https://philterd.ai/use-cases/ai/index.md): Redact PII from prompts before they reach an LLM provider, with Philter AI Proxy for applications and Philter MCP for agents. Open source and self-hosted. - [PII Redaction for AI Training Data](https://philterd.ai/use-cases/ai-training/index.md): De-identify training and fine-tuning data in your own cloud before it reaches a model, with human review for uncertain cases and measured accuracy. - [PII Redaction for Contact Centers](https://philterd.ai/use-cases/contact-center/index.md): Redact names, card numbers, and contact details from call and chat transcripts in your own cloud, before they reach QA, analytics, or AI tools. - [PII Redaction for Education and EdTech](https://philterd.ai/use-cases/education/index.md): Redact student records in your own cloud with Philter, or on a Windows PC with Philter Desktop. For universities, school districts, edtech, and registrars. - [PII Redaction for Financial Services](https://philterd.ai/use-cases/finance/index.md): Redact card numbers, account data, and SSNs in your own cloud with Philter, or on a Windows PC with Philter Desktop. For banks, fintech, and accountants. - [PII Redaction for Government](https://philterd.ai/use-cases/government/index.md): Redact records in your own environment, even air-gapped, with Philter, or on a Windows PC with Philter Desktop. For agencies, clerks, and records officers. - [PII Redaction for Insurance](https://philterd.ai/use-cases/insurance/index.md): Redact claims, policy, and customer data in your own cloud with Philter, or on a Windows PC with Philter Desktop. For carriers and independent agencies. - [PII Redaction for Law Firms](https://philterd.ai/use-cases/legal/index.md): Redact court filings and client documents on your own Windows PC with Philter Desktop. Offline, no IT team needed, and configurable for FRBP 9037 and FRCP 5.2. ## Comparisons with other PII redaction tools - [Philter Comparisons](https://philterd.ai/compare/index.md): How Philter compares with AWS Comprehend, Google Cloud DLP, Presidio, Private AI, Skyflow, and CaseGuard. Honest trade-offs from the people who built it. - [Philter Desktop vs CaseGuard](https://philterd.ai/compare/philter-desktop-vs-caseguard/index.md): Philter Desktop vs CaseGuard for document redaction: price, offline use, file types, and open source, plus when CaseGuard's video and audio tools are worth it. - [Philter vs Private AI (PII Redaction)](https://philterd.ai/compare/philter-vs-private-ai/index.md): How Philter and Private AI compare for PII and PHI redaction: open source vs closed-source, self-hosting, language coverage, policy depth, and pricing. - [Philter vs Skyflow (Redaction vs Data Privacy Vault)](https://philterd.ai/compare/philter-vs-skyflow/index.md): Philter and Skyflow solve different problems: Philter redacts PII in your pipeline, Skyflow is a vault that tokenizes it. How they differ and when each fits. - [Philter and Phileas vs Microsoft Presidio](https://philterd.ai/compare/philter-vs-microsoft-presidio/index.md): Philter and Phileas vs Microsoft Presidio: open source PII redaction as a library or a self-hosted service, compared on runtimes, policies, and support. - [Philter vs AWS Comprehend (PII Detection)](https://philterd.ai/compare/philter-vs-aws-comprehend/index.md): How Philter and AWS Comprehend PII detection compare on data path, pricing, cloud portability, and customization, for teams actively evaluating both. - [Philter vs Google Cloud DLP](https://philterd.ai/compare/philter-vs-google-cloud-dlp/index.md): How Philter and Google Cloud DLP (Sensitive Data Protection) compare on data path, multi-cloud portability, customization depth, and TCO at production volumes. ## Migrating to Philter - [Migrate to Philter](https://philterd.ai/migrate/index.md): Practical guides for moving from AWS Comprehend, Microsoft Presidio, Google Cloud DLP, Private AI, and Skyflow to Philter. Concept mapping and cost comparisons. - [Migrate from Private AI to Philter](https://philterd.ai/migrate/from-private-ai/index.md): A practical guide to migrating from Private AI to Philter: concept mapping, API request-shape translation, replacement mapping, and a safe shadow-mode cutover. - [Migrate from Skyflow to Philter](https://philterd.ai/migrate/from-skyflow/index.md): Moving from a Skyflow data privacy vault to Philter is a re-architecture, not an API swap. When the move makes sense, and how to translate it safely. - [Migrate from AWS Comprehend to Philter](https://philterd.ai/migrate/from-comprehend/index.md): A practical migration guide from AWS Comprehend's PII detection to Philter. Concept mapping, code translation, shadow-mode cutover, and cost comparison. - [Migrate from Google Cloud DLP to Philter](https://philterd.ai/migrate/from-google-dlp/index.md): A practical migration guide from Google Cloud DLP to Philter: concept mapping, infoType translation, deployment differences, and cost at production volumes. - [Migrate from Microsoft Presidio to Philter](https://philterd.ai/migrate/from-presidio/index.md): A practical migration guide from Microsoft Presidio to Philter. Recognizer mapping, deployment differences, policy translation, and what changes operationally. ## Knowledge base - [Knowledge Base](https://philterd.ai/guides/index.md): How-tos, troubleshooting, reference, and concepts for PII and PHI redaction with Philter, Phileas, Philter Desktop, and the rest of the Philterd toolkit. - [Alerting on PII Spikes with Phield and Slack](https://philterd.ai/guides/alert-on-pii-spikes-with-phield/index.md): Alert in Slack when PII counts spike with Phield: send per-batch counts from your pipeline, read the breach alerts, and tune the threshold with replay. - [Build and test a redaction policy without writing JSON](https://philterd.ai/guides/build-and-test-a-redaction-policy-without-json/index.md): Build a redaction policy in the Redaction Policy Editor, test it on sample text, and download JSON for Philter or Phileas without writing it by hand. - [Find the PII in a Folder of Files Before You Share or Migrate It](https://philterd.ai/guides/find-pii-in-a-folder-with-phinder/index.md): Scan a folder for PII with Phinder before you share or migrate it, and get a risk-ranked report of which files hold SSNs, email addresses, and other PII. - [Measure Philter's Redaction Accuracy on Your Own Documents](https://philterd.ai/guides/measure-redaction-accuracy-with-philter-scope/index.md): Measure PII redaction precision and recall on your own documents with Philter Scope: label a gold-standard set, audit a Philter policy, read the report. - [Philter Desktop Blocked by Smart App Control or App Control for Business](https://philterd.ai/guides/philter-desktop-blocked-by-smart-app-control/index.md): Fix "An application control policy has blocked this file" when starting Philter Desktop. Update to 1.3.1, which signs every file Smart App Control checks. - [Publish PII counts with differential privacy instead of exact numbers](https://philterd.ai/guides/publishing-pii-counts-with-differential-privacy/index.md): Publish PII counts with differential privacy using Philter Diffuse: choose the types, set the noise scale, and track the privacy budget across releases. - [Review Redactions Before Release: Thresholds, Sampling, and Sign-off in Philter Workspace](https://philterd.ai/guides/philter-workspace-review-thresholds-and-sign-off/index.md): Set the PII threshold, audit sampling rate, and approval rules in Philter Workspace to decide which redactions a person reviews and who signs off. - [Running Philter Desktop on an Apple Silicon Mac with Parallels](https://philterd.ai/guides/running-philter-desktop-on-a-mac-with-parallels/index.md): Run Philter Desktop in Windows 11 on ARM under Parallels on an Apple Silicon Mac. Install the Visual C++ ARM64 runtime first so name detection loads. - [Span Disambiguation: What It Does and When to Enable It](https://philterd.ai/guides/span-disambiguation/index.md): When two Phileas filters claim the same text with different types, span disambiguation picks one. When it helps, what it costs, and how to run it. - [Philter Desktop Quick Start, from Install to First Redacted Document](https://philterd.ai/guides/philter-desktop-quick-start/index.md): Install Philter Desktop on Windows, set up a redaction policy, redact your first document, and review the draft before you share it. Nothing gets uploaded. - [Redact a Folder of Documents Automatically on Windows](https://philterd.ai/guides/redact-a-folder-of-documents-automatically/index.md): Point Philter Desktop at a folder and new files get redacted as they arrive. Watched folders, a command line, and a right-click action, all running on your PC. - [Self-Hosted Philter Reference Architectures](https://philterd.ai/guides/self-hosted-philter-reference-architectures/index.md): Reference architectures for running self-hosted Philter inside your own AWS, Azure, or GCP boundary, with no-egress and government-cloud variants. - [Redacting PII in Apache Kafka](https://philterd.ai/guides/redacting-pii-in-apache-kafka/index.md): Redact PII and PHI in Apache Kafka with the philter-kafka-connect Single Message Transform, on source, sink, or MirrorMaker connectors. - [Authoring Redaction Policies with PhiSQL](https://philterd.ai/guides/authoring-redaction-policies-with-phisql/index.md): PhiSQL is a readable query language that compiles to a Phileas redaction policy. An introduction to the syntax and how it maps to the policy JSON. - [Modern Privacy Techniques, and When to Use Each](https://philterd.ai/guides/modern-privacy-techniques-and-when-to-use-each/index.md): A practical map of privacy techniques: redaction, pseudonymization, encryption, generalization, differential privacy, and synthetic data, and when each fits. - [Redacting National and Financial ID Numbers](https://philterd.ai/guides/redacting-national-and-financial-id-numbers/index.md): A how-to for redacting national and financial IDs (SIN, CPF, DNI, IBAN, BIC, and more) with checksum-validated patterns that reject look-alikes. - [Redacting PII in Logs with log4j2 and logback](https://philterd.ai/guides/redacting-pii-in-logs-with-log4j2-and-logback/index.md): How to redact PII from Java logs before they are written, with a Phileas-backed log4j2 rewrite policy and a logback converter, recursion guard included. - [Redacting PII in Spark and Databricks](https://philterd.ai/guides/redacting-pii-in-spark-and-databricks/index.md): Redact PII column by column in Apache Spark and Databricks with a Phileas UDF: a verified PySpark example, plus the performance tradeoffs to plan for. - [Redacting PII in Trino with the Phileas Connector](https://philterd.ai/guides/redacting-pii-in-trino-with-the-phileas-connector/index.md): How to install the open source Phileas connector for Trino, configure a redaction policy, and mask PII column by column in SQL, with a runnable demo. - [Self-Hosted PII Detection on Your Own Hardware](https://philterd.ai/guides/self-hosted-pii-detection-on-your-own-hardware/index.md): Run PII detection entirely inside your own boundary: serve the models with PhEye, embed Phileas, or run local ONNX inference, with no data egress. - [PIPEDA and Law 25: PII Redaction for Canadian Privacy Compliance](https://philterd.ai/guides/pipeda-and-law-25-pii-redaction-canadian-privacy-compliance/index.md): How Philter addresses PIPEDA and Quebec's Law 25: self-hosted deployment for data residency, bilingual redaction, and Canadian identifier handling. - [What is NPPI? Nonpublic Personal Information, Defined](https://philterd.ai/guides/what-is-nppi-nonpublic-personal-information/index.md): NPPI (Nonpublic Personal Information) is the financial data GLBA protects. See what counts as NPPI, what's excluded, and how it differs from PII and PHI. - [SOC 2 and HIPAA Control Mapping for Philter AI Proxy](https://philterd.ai/guides/soc-2-and-hipaa-control-mapping-for-philter-ai-proxy/index.md): Map Philter AI Proxy features to SOC 2 Trust Services Criteria and HIPAA Security Rule safeguards, with guidance for your own attestations. - [Apache NiFi and Philter](https://philterd.ai/guides/apache-nifi-and-philter/index.md): How to use Philter to redact PII and PHI inside an Apache NiFi data flow, either through Philter's API or with an embedded NiFi processor. - [Deploying Philter in a HIPAA Environment](https://philterd.ai/guides/deploying-philter-in-a-hipaa-environment/index.md): How to configure a Philter deployment for HIPAA: encryption of data at rest and in motion across AWS, Azure, and Google Cloud. - [Deploying Philter in AWS via a CloudFormation Template](https://philterd.ai/guides/deploying-philter-with-aws-cloudformation/index.md): How to deploy Philter in AWS with a CloudFormation template: finding the Philter AMI, editing the template, and launching the stack. - [How to Use a Signed SSL Certificate with Philter](https://philterd.ai/guides/using-a-signed-ssl-certificate-with-philter/index.md): How to replace Philter's self-signed certificate with one signed by a trusted authority, using a PKCS12 keystore and two settings. - [How to Use an Apache Reverse Proxy with Philter](https://philterd.ai/guides/using-an-apache-reverse-proxy-with-philter/index.md): How to run an Apache reverse proxy in front of Philter for SSL termination, access control, and access logging. - [Monitoring Philter in AWS](https://philterd.ai/guides/monitoring-philter-in-aws/index.md): How to monitor Philter in AWS: CloudWatch Logs for its log, load balancer health checks for availability, and its Prometheus metrics. - [Referential Integrity with Valkey](https://philterd.ai/guides/referential-integrity-with-valkey/index.md): How to configure a Valkey cache so Philter maintains referential integrity (consistent replacement values) across documents and contexts in a cluster. - [The Phileas redaction policy schema](https://philterd.ai/guides/redaction-policy-schema/index.md): What a redaction policy is, how the JSON schema is structured, and how to use it to control exactly which PII is detected and how each type is redacted. - [Using Philter with Microsoft Power Automate](https://philterd.ai/guides/using-philter-with-microsoft-power-automate/index.md): How to call Philter from a Microsoft Power Automate (Flow) automation to redact PII and PHI from text, using a simple HTTP action. - [Why Philterd Doesn't Need to Sign a BAA](https://philterd.ai/guides/why-philterd-doesnt-sign-a-baa/index.md): Philterd's software runs inside your own infrastructure and sends your PHI nowhere, so for the software there is no business associate and no BAA to sign. - [Writing your first redaction policy](https://philterd.ai/guides/writing-your-first-redaction-policy/index.md): A hands-on walkthrough from empty file to working redaction policy: detect an entity, apply it with Philter, change how it redacts, and handle false positives. - [What is PII? A Practical Guide for Engineers and Compliance Teams](https://philterd.ai/guides/what-is-pii-a-practical-guide-for-engineers-and-compliance-teams/index.md): PII is the term everyone uses and few define the same way. A practitioner's guide to what counts as PII, how to find it in real data, and how to handle it. - [The Hidden Difficulties of Redacting PDF Documents](https://philterd.ai/guides/the-hidden-difficulties-of-redacting-pdf-documents/index.md): PDFs leak redacted text in unexpected ways: invisible text layers, embedded files, and metadata. Why PDF redaction is harder than it looks, with Philter's fix. - [Prompt Engineering for Privacy: Practical Patterns for Not Leaking PII](https://philterd.ai/guides/prompt-engineering-for-privacy/index.md): Every prompt sent to an LLM is a data egress point. Six concrete patterns for structuring prompts, redacting inputs, and scanning outputs so PII doesn't leak. - [PII in Vector Embeddings: A Defense Guide](https://philterd.ai/guides/pii-in-vector-embeddings-a-defense-guide/index.md): Embeddings look like just numbers, but research shows they are partially invertible. A practical defense guide for vector stores against PII recovery attacks. - [PII vs PHI vs NPPI: An Engineer's Guide](https://philterd.ai/guides/pii-vs-phi-vs-nppi-an-engineers-guide/index.md): PII, PHI, and NPPI are not interchangeable. What each covers, which law governs it, how they overlap, and a decision tree for classifying your own data. - [What is Data Redaction? A Practical Guide](https://philterd.ai/guides/what-is-data-redaction-a-practical-guide/index.md): Data redaction removes sensitive information from documents and datasets, but covers more techniques than most realize. A guide to strategies and trade-offs. - [Using an LLM or Pattern-based Rules for PII/PHI Redaction](https://philterd.ai/guides/using-an-llm-or-pattern-based-rules-for-pii-phi-redaction/index.md): Comparing the two main approaches to redacting PII and PHI: an LLM versus pattern-based rules. How each handles accuracy, cost, and GDPR or HIPAA compliance. - [Redacting Text in Amazon Kinesis Data Firehose](https://philterd.ai/guides/redacting-text-in-amazon-kinesis-data-firehose/index.md): Amazon Kinesis Firehose is a managed streaming service that moves data from sources to destinations like S3 and Redshift. This post redacts PII in that stream. - [What is format-preserving encryption?](https://philterd.ai/guides/what-is-format-preserving-encryption/index.md): Format-preserving encryption (FPE) encrypts a value so the ciphertext keeps its shape and won't break downstream systems. A guide with credit-card examples. - [PhEye Support](https://philterd.ai/support/ph-eye/index.md): Get help with PhEye, the PII detection models and model server: self-hosting detection, the documentation, and the issue tracker. - [Phield Support](https://philterd.ai/support/phield/index.md): Get help with Phield, which monitors where PII flows: setup and alerting guides, the documentation, and the issue tracker. - [Phileas Support](https://philterd.ai/support/phileas/index.md): Get help with Phileas, the PII redaction library: redaction policies, Kafka, Spark, Trino, and logging guides, the docs, and the issue tracker. - [Philter AI Proxy Support](https://philterd.ai/support/philter-ai-proxy/index.md): Get help with Philter AI Proxy, which redacts PII from LLM prompts: privacy patterns, control mappings, the documentation, and issues. - [Philter Desktop Support](https://philterd.ai/support/philter-desktop/index.md): Get help with Philter Desktop, the offline redaction app for Windows: troubleshooting, how-tos, the documentation, and how to reach support. - [Philter Diffuse Support](https://philterd.ai/support/philter-diffuse/index.md): Get help with Philter Diffuse, for differential privacy on PII analytics: guides, the documentation, and the issue tracker. - [Philter Scope Support](https://philterd.ai/support/philter-scope/index.md): Get help with Philter Scope, which measures redaction precision and recall: guides, the documentation, and the issue tracker. - [Philter Support](https://philterd.ai/support/philter/index.md): Get help with Philter, the self-hosted PII redaction API: deployment and operations guides, the documentation, and how to reach support. - [Philter Workspace Support](https://philterd.ai/support/philter-workspace/index.md): Get help with Philter Workspace, for human review of redactions: review workflow guides, the documentation, and the issue tracker. - [Phinder Support](https://philterd.ai/support/phinder/index.md): Get help with Phinder, which finds PII in files at rest: scanning folders, reading reports, the documentation, and the issue tracker. - [PhiSQL Support](https://philterd.ai/support/phisql/index.md): Get help with PhiSQL, the query language for redaction policies: writing policies in PhiSQL, the documentation, and the issue tracker. - [Redaction Policy Editor Support](https://philterd.ai/support/redaction-policy-editor/index.md): Get help with the Redaction Policy Editor, a visual builder for redaction policies: guides, the documentation, and the issue tracker. ## Developers - [Build with Philterd](https://philterd.ai/dev/index.md): Quickstarts, runnable samples, and reference docs for the open source PII and PHI redaction toolkit. - [Choose a tool](https://philterd.ai/dev/choose/index.md): Which Philterd project matches what you are building. - [Get involved](https://philterd.ai/dev/get-involved/index.md): Where the code lives, how to ask a question, how to contribute, and how to sign off your commits. - [Packages & distributions](https://philterd.ai/dev/packages/index.md): Every Philterd open source distribution on Maven Central, NuGet, PyPI, and Hugging Face, with the current published version of each, refreshed automatically. - [Philter AI Proxy: quick start](https://philterd.ai/dev/start/philter-ai-proxy/index.md): Run Philter AI Proxy in Docker, create a key for your application, and send a prompt that reaches OpenAI with its PII redacted. - [Philter on AWS: quick start](https://philterd.ai/dev/start/aws/index.md): Launch Philter from AWS Marketplace, read its API key over SSH, and redact your first text with one curl command. - [Philter on Azure: quick start](https://philterd.ai/dev/start/azure/index.md): Launch Philter from Azure Marketplace, read its API key over SSH, and redact your first text with one curl command. - [Philter on Google Cloud: quick start](https://philterd.ai/dev/start/google-cloud/index.md): Launch Philter from Google Cloud Marketplace, read its API key over SSH, and redact your first text with one curl command. - [PII detection models](https://philterd.ai/dev/models/index.md): Run PhEye to detect person names with an AI model, choose a lens, and connect it to Phileas or Philter. - [Redaction policies](https://philterd.ai/dev/policies/index.md): Start from a pre-defined Philterd redaction policy, then adapt it and apply it in Phileas, Philter, or PhiSQL. - [Reference](https://philterd.ai/dev/reference/index.md): Per-product documentation, configuration, and API details. - [Your first redaction](https://philterd.ai/dev/start/index.md): Redact PII from a string in about five minutes, over HTTP with Philter or in your own code with Phileas. ## Company - [About Us: The Open Source PII Redaction Company](https://philterd.ai/company/index.md): Meet the team behind Philter: open source, self-hosted PII and PHI redaction built and maintained by the people who wrote it, under Apache-2.0. - [Philterd Architecture Overview](https://philterd.ai/architecture/index.md): How Philter, Phileas, PhEye, the AI Proxy, Phinder, Phield, Philter Workspace, Scope, Diffuse, and the Policy Editor form a self-hosted PII redaction stack. - [Open Source PII Redaction Software](https://philterd.ai/open-source-software/index.md): Open source PII and PHI redaction you self-host. Apache-2.0 licensed and free to run on your desktop or in your cloud. Helps meet HIPAA and GDPR compliance. - [Compliance Matrix](https://philterd.ai/compliance/index.md): Which Philterd products address which regulations: HIPAA, GDPR, PIPEDA, Law 25, CCPA, PCI DSS, GLBA, FERPA, SOX, FedRAMP, and more. For your security review. - [Security & Trust](https://philterd.ai/security/index.md): How Philterd is built, how vulnerabilities are disclosed, and where your data lives. - [Integrations](https://philterd.ai/integrations/index.md): Platforms, services, and frameworks that Philterd's open source PII redaction toolkit integrates with. Every integration runs self-hosted inside your perimeter. - [Case Studies](https://philterd.ai/case-studies/index.md): How organizations use Philterd to solve real PII and PHI redaction problems in healthcare, finance, and AI workloads. - [Community](https://philterd.ai/community/index.md): How to participate in the Philterd open source community: GitHub, discussions, contributing, roadmap, releases, and how to reach the maintainers. - [Best PII Redaction Software: Self-Hosted and Cloud Options](https://philterd.ai/best-pii-redaction-software/index.md): Compare 9 PII redaction tools: Philter, Presidio, AWS Comprehend, Google DLP, Azure, and more. Self-hosted vs cloud, detection methods, and how to choose. - [PII Redaction](https://philterd.ai/pii-redaction/index.md): PII redaction software you run yourself. Philter redacts PII in your pipelines and APIs, and Philter Desktop redacts documents on a Windows PC. Open source. - [PHI Redaction](https://philterd.ai/phi-redaction/index.md): PHI redaction software you self-host. Redact HIPAA Safe Harbor identifiers from clinical text in your own VPC. Open source, and it runs in your own environment. - [Philter Open Source License (Apache 2.0)](https://philterd.ai/philter-license-agreement/index.md): Philter is open source software licensed under the Apache License, Version 2.0. This page states the license and includes the full license text. ## Optional - [Redaction Policies](https://philterd.ai/policies/index.md): A browsable, community-curated library of Philter and Phileas redaction policies. Covers HIPAA, PCI DSS, FRBP 9037, AI training data, and more. Apache 2.0. - [Philterd Labs](https://philterd.ai/labs/index.md): Experimental and early-stage open source projects from Philterd. Usable and Apache-2.0 licensed, but earlier than the rest of the PII redaction toolkit. - [Search Redact](https://philterd.ai/search-redact/index.md) (experimental, part of Philterd Labs): Search Redact is an open source plugin that redacts PII and PHI from OpenSearch and Elasticsearch search results before they reach end users. - [Philter MCP](https://philterd.ai/philter-mcp/index.md) (experimental, part of Philterd Labs): Philter MCP is an open source Model Context Protocol server exposing PII and PHI redaction to Claude Desktop, Claude Code, Cursor, and other MCP clients. - [Philter Router](https://philterd.ai/philter-router/index.md) (experimental, part of Philterd Labs): Philter Router routes files to the right Philter engine and redaction policy from content type, filename, directory, and a local-LLM classification. - [Blog](https://philterd.ai/blog/index.md): Articles on PII and PHI redaction, AI privacy, and the Philterd toolkit. Recent posts: - [Introducing Phield: Monitoring How PII Actually Moves Through Your Systems](https://philterd.ai/blog/introducing-phield-pii-drift-monitoring/index.md): Phield is a PII drift and trend monitor. It takes PII type counts over an API or Kafka, builds a baseline, and alerts via PagerDuty or Slack on deviations. - [Announcing Philter 4, the Most Capable Philter Yet](https://philterd.ai/blog/announcing-philter-4/index.md): Philter 4 is out. It is API-only, stores data in SQLite or MongoDB, adds a tamper-evident redaction ledger, and tightens security defaults. See what changed. - [Philter Desktop 1.2.0 Adds ITIN and SIN Detection and Keep-Last-4 Redaction](https://philterd.ai/blog/philter-desktop-1-2-0-itin-sin-and-new-redaction-strategies/index.md): Philter Desktop 1.2.0 detects ITINs and Canadian SINs and adds strategies like keeping the last 4 digits of a card number, masking, hashing, and encryption. - [Philterd Joins the gBETA Fall 2026 Cohort at Marshall's iCenter](https://philterd.ai/blog/philterd-joins-gbeta-marshall-fall-2026-cohort/index.md): Philterd is one of five West Virginia companies in the gBETA at Marshall's iCenter Fall 2026 cohort, a free seven-week accelerator run with gener8tor. - [Show Me the Code Path: Why Open Source Wins the PII Redaction Audit](https://philterd.ai/blog/show-me-the-code-path-open-source-pii-redaction-audit/index.md): When an auditor asks how a redaction decision was made, open source lets you answer with the code path. A decisive edge for government and healthcare buyers. - [Redaction Policies as Code: Building and Sharing Policies with the Philterd Policy Library](https://philterd.ai/blog/redaction-policies-as-code/index.md): A redaction policy decides what leaves your building. Treating it as a versioned, tested file rather than a console setting is what makes it reviewable. - [Redacting PII and PHI from Audio Transcriptions with Philter and Amazon Transcribe](https://philterd.ai/blog/redacting-audio-transcriptions-with-philter-and-amazon-transcribe/index.md): A hands-on guide to redacting PII and PHI from audio transcripts. Run Philter against an Amazon Transcribe transcript and deploy two AWS architectures at scale. - [Integrating Philter AI Proxy with OpenAI and Anthropic in Production](https://philterd.ai/blog/philter-ai-proxy-openai-anthropic-production/index.md): Pointing a client at the proxy is one line. Where it sits relative to your AI gateway, and what it does with streaming responses, are the parts to get right. - [Air-Gapped PII Redaction for Government: A Deployment Walkthrough](https://philterd.ai/blog/air-gapped-redaction-deployment-walkthrough/index.md): A walkthrough for standing up Philter 3.4.2 and PhEye in a disconnected enclave: pinned images, offline transfer, and proving there is no egress. - [Five Ways a Healthcare App Leaks PHI Without Anyone Noticing](https://philterd.ai/blog/five-ways-a-healthcare-app-leaks-phi/index.md): The demo looks clean. Here are five places PHI quietly ends up in a fast-built healthcare app, why each one happens, and what to do about it. - [Redact PDFs Offline on Windows so No Data Leaves Your PC](https://philterd.ai/blog/redact-pdfs-offline-on-windows/index.md): Philter Desktop redacts PDFs entirely on your Windows PC, including scanned pages read with on-device OCR. No uploads, no server, and it works offline. - [The Clean Room for AI Training Data: Redact, Review, Measure](https://philterd.ai/blog/the-clean-room-for-ai-training-data-redact-review-measure/index.md): Once PII is baked into model weights it is extractable for the model's life. The clean room pattern: Philter redacts, Arbiter reviews, Philter Scope measures. - [When a PDF Is Too Dense to Redact](https://philterd.ai/blog/when-a-pdf-is-too-dense-to-redact/index.md): Redacting a 400-page file with PII on every line leaves a compliant document nobody can use. Distill it into the facts downstream needs, then redact those. - [Moving PII Redaction Off the CPU: An FPGA Experiment](https://philterd.ai/blog/moving-pii-redaction-off-the-cpu-an-fpga-experiment/index.md): I put a streaming SSN redaction engine on an FPGA. It sits inline on the wire, so bytes get redacted before they reach a CPU, host memory, or an OS. - [Redact Both Sides of the LLM: Inputs and Outputs](https://philterd.ai/blog/redact-both-sides-of-the-llm-inputs-and-outputs/index.md): Prompt redaction protects the provider boundary. Output scanning protects everything downstream. An LLM needs PII redaction on both sides, not one.