Skip to content
@DataFog

DataFog

Local PII protection for AI applications. Open-source detection and privacy transformations across Rust, Python, Node.js, and browsers.

DataFog

Local PII protection for AI applications.

DataFog helps developers detect sensitive information in text and structured records, then choose how to protect it before passing it to a model, a log, or another system.

Start with DataFog Core — our Rust engine with SDKs for Python, Node.js, and browsers. Redact, mask, or remove sensitive values across runtimes. Use application-supplied providers for pseudonymization and reversible tokenization in Rust, Python, and Node.js.

Get started · Documentation · Try the demo

Choose your starting point

Repository Role
datafog-core Recommended starting point for new applications. Shared detection and transformation engine, with Rust, Python, Node.js, and browser SDKs.
datafog-python Established Python package, including the Claude Code hook and LiteLLM guardrail adapter. Moving to Core? Follow the migration guide.
datafog-claude-plugin Claude Code integration, with its own setup and release path.
fogclaw OpenClaw integration for PII detection and redaction.

Core is a separate package and API from the established datafog Python library. Existing integrations have their own capabilities and release paths; Core adoption is a separate next step.

Build with Core

  • Detect: scan text and parsed JSON records, including supported person-name fields, with local built-in detectors.
  • Transform: redact, mask, remove, pseudonymize, or tokenize selected values. Select entity types, apply per-entity rules, and exempt approved values.
  • Restore: restore provider-issued tokens under an exact request scope. Your provider owns storage and authorization.

Browser SDKs support detection and stateless transformations. Provider-backed pseudonymization, tokenization, and restoration are available in Rust, Python, and Node.js. See the SDK installation guide and transformation guide.

Core supplies detection and transformation. Your application or integration chooses where to invoke it and how to enforce policy.

Where we’re going

One shared privacy engine across more application, agent, and gateway workflows. Core owns detection and transformation; integrations connect that behavior to the places data moves, including workflow-specific interception and enforcement.

Follow the Core roadmap for implementation status and the release notes for shipped capabilities.

Links

Website · Documentation · Installation · Contributing · Discord

Pinned Loading

  1. datafog-core datafog-core Public

    PII detection and privacy transformations for text and structured records. Built in Rust, with Python, Node.js, and browser SDKs.

    Rust

  2. datafog-python datafog-python Public

    Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

    Python 71 14

  3. datafog-claude-plugin datafog-claude-plugin Public

    Offline PII firewall plugin for Claude Code — blocks emails, cards, SSNs in agent tool calls before they leave your machine

    Shell

  4. fogclaw fogclaw Public

    OpenClaw plugin for PII detection & custom entity redaction powered by DataFog

    TypeScript 1

Repositories

Showing 10 of 16 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…