On-Premise, Open Source PII Redaction Software

Which open source Philterd tool do I need?

Every tool in the Philterd toolkit is open source and free to run. Start from what you're trying to do, and each path maps to the tools that solve it.

I want to redact PII

Pick the surface that matches where the text lives: an API, an embedded library, or an LLM gateway.

Philter → Self-hosted redaction API. Drops into any HTTP-based pipeline.
Phileas → The same engine as a library in Java, Python, and .NET. No service hop.
Philter AI Proxy → Drop-in proxy for OpenAI and Anthropic. One URL change.

I want to find and watch PII

Map where PII already lives, then watch how it moves through the systems you care about.

Phinder → Discovery scanner that crawls files and storage to find PII at rest.
Phield → Flow monitoring that tracks how PII moves and alerts on suspicious activity.

I want to author, review, and measure policies

Build the policy, override what the system gets wrong, and measure how well it works over time.

Redaction Policy Editor → Visual no-code builder for compliance teams.
PhiSQL → Declarative DSL. Policy-as-code for engineering teams.
Arbiter → Human-in-the-loop review with structured exemption codes.
Philter Scope → Benchmarks precision, recall, and F1 so you can tune with numbers.

The Open Source PII Toolkit

A complete stack for finding, redacting, monitoring, and auditing sensitive data, from low-level libraries to turnkey services. Each project is released under the permissive, business-friendly Apache License and developed in the open on GitHub.

Core redaction

The engine and API that find and redact PII in text.

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.

Star 47 Deploy →

Learn more → GitHub → Docs →

Redaction Library Java

Phileas for Java

The core redaction, anonymization, masking, and replacement library underneath Philter. The original Java implementation, with checksum-validated identifiers for national and financial IDs.

Star 99

Learn more → GitHub → Docs →

Redaction Library Python

Phileas for Python

The Python implementation of the Phileas redaction library, for embedding PII detection and redaction directly in Python services and data pipelines.

Star 2

Learn more → GitHub → Docs →

Redaction Library .NET

Phileas for .NET

The .NET implementation of the Phileas redaction library, for embedding PII detection and redaction in .NET applications.

Star 1

Learn more → GitHub → Docs →

Desktop app .NET

Philter Desktop

Offline Windows desktop app that redacts PII from PDF, Microsoft Word, and text files entirely on your own machine, using the same policy engine as Philter. In active development.

Star

Learn more → GitHub →

Search plugin Java

Search Redact for OpenSearch

OpenSearch plugin that redacts PII and PHI from search results at query time, built on Phileas. Runs inside your cluster so sensitive fields are redacted before results reach the user.

Star 2

Learn more → GitHub → Docs →

Search plugin Java

Search Redact for Elasticsearch

Elasticsearch plugin that redacts PII and PHI from search results at query time, built on Phileas. The Elasticsearch build of the same query-time redaction, for clusters running Elasticsearch.

Star 1

Learn more → GitHub → Docs →

AI models & LLM guardrails

Trained models and drop-in proxies for AI workloads.

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.

Star 1

Learn more → GitHub → Docs →

LLM proxy Go

Philter AI Proxy

Drop-in proxy that redacts PII and PHI before prompts reach LLM providers like OpenAI and Anthropic Claude.

Star 3

Learn more → GitHub → Docs →

MCP server Python

Philter MCP

MCP server that exposes Philter's PII and PHI redaction as tools for Claude Desktop, Claude Code, Cursor, and other MCP-aware clients. Redact inside the agent's tool loop, with no integration code.

Star 1

Learn more → GitHub →

Discovery & monitoring

Find where PII lives and watch where it flows.

Discovery Java

Phinder

High-speed discovery scanner that crawls files and storage to map where sensitive information actually lives across your environment.

Star 1

Learn more → GitHub → Docs →

Monitoring Go

Phield

Intelligent monitoring that tracks PII flow across the organization and alerts on suspicious activity or unusual trends.

Star 2

Learn more → GitHub → Docs →

Review, policy & operations

Human review, policy authoring, benchmarking, and privacy analytics.

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.

Star 1

Learn more → GitHub → Docs →

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.

Star 1

Learn more → GitHub → Docs →

Differential privacy Python

Philter Diffuse

Privacy-first analytics that applies differential privacy to PII counts, preserving statistical utility without exposing individuals.

Star 1

Learn more → GitHub → Docs →

Policy editor JavaScript

Redaction Policy Editor

Web console that lets non-technical users build and deploy redaction rules through a visual, no-code interface.

Star 1

Learn more → GitHub → Docs →

Query language Java

PhiSQL

Declarative query language for PII operations. Write readable redaction policies as code that compile to the standard Phileas JSON schema.

Star 1

Learn more → GitHub →

Not sure which one to start with? Walk through the PII redaction journey → · See how they all connect →

Philterd builds open source software for finding and redacting PII and PHI in text. Every tool is released under the permissive, business-friendly Apache License, Version 2.0, and developed in the open on GitHub. You can read the source, run it for free, and self-host it inside your own cloud or data center. See PHI redaction for the HIPAA-specific workflow.

Why open source, self-hosted redaction

Redaction decides your compliance boundary, and the boundary is what an auditor examines. If sensitive text has to leave your network to be redacted by a hosted service, the exposure has already happened. The open source, self-hosted approach removes that problem at the root:

Your data never leaves your perimeter. Philter runs inside your VPC or on-premises, so customer names, Social Security numbers, medical record numbers, and account IDs are redacted before anything crosses the wire. This is what keeps HIPAA, GDPR, and PCI scope defensible.
No vendor lock-in. Apache-2.0 means no license keys, no per-seat fees, and no commercial review. Run it on AWS, Google Cloud, Azure, on-premises, or air-gapped.
Auditable by design. The detection logic is purpose-built NLP and pattern matching that you can read, test, and version, not a black box. Policies are versioned artifacts, so “what did we redact, and how, on this date” is answerable with a diff.
Free to run. The full toolkit is free under the open source tier. Commercial paths exist for teams that want one-click marketplace deploys or hands-on engineering, but the code is never gated.

Apache-2.0 licensed

Every Philterd project is released under the Apache License, Version 2.0. You are free to use, modify, and distribute it under the terms of that license, with no per-seat fees and no usage caps. See the full Philter license for details, and browse all of the source on the Philterd GitHub organization .

Get started

You can run the open source toolkit from source for free, or deploy the turnkey Philter API in minutes from your cloud marketplace with per-hour billing inside your existing account:

See pricing for how the open source, marketplace, and engaged tiers compare.

Compare and explore

Weighing your options? Start with the overview of the best PII redaction software .

See how Philter compares to other tools: Microsoft Presidio , AWS Comprehend , Google Cloud DLP , Private AI , and Skyflow .

Or see it by industry: healthcare , finance , legal , government , and insurance .

New to redaction? Start with what PII is , running detection on your own hardware , and writing your first redaction policy .

FAQ

Is Philter really free and open source?

Yes. The full toolkit is on GitHub under the Apache License, Version 2.0. There are no license keys, no usage caps, and no commercial review. Self-host it on whatever infrastructure you want. Philterd earns revenue from cloud-marketplace deployments and engaged consulting, not from gating the code.

Can I self-host PII redaction in my own cloud?

Yes, and that is the point. Philter and the rest of the toolkit run inside your own VPC, on-premises, or air-gapped environment, so sensitive text is redacted before it ever leaves your network. Nothing is sent to a vendor in order to be redacted.

What license is the software under?

The Apache License, Version 2.0, a permissive and business-friendly open source license. You can read the full Philter license on this site.