See all product releases ↓

Local PII protection.
Across your workflow.

Protect sensitive data in your applications, check files before your AI agent reads them, and build encrypted local storage.

Choose datafog core, datafog MCP, fogvault, or the datafog Python library. Each product has its own release track.

python -m pip install datafog-core

Install the Core SDK in your application. Installation guide ↗

Products & releases

Find your starting point.
See what’s new.

From application code to agent workflows and encrypted storage. Pick the product you need and follow its release track.

Release snapshot ·

Embed the privacy engine

datafog core

1.7.0 ↗

Released

Local PII and credential detection and privacy transformations, with SDKs for Rust, Python, Node.js, and browsers.

In this release Restores email and phone detections missed in Core 1.5 and 1.6.

Protect files before your agent reads them

datafog MCP

1.1.0 ↗

Released

Scan local files and create redacted, masked, or cleaned copies. Your agent receives counts and paths rather than matched values.

In this release Core 1.7 detection fixes, a reusable Python scanning interface, and vault-directory exclusions.

Build encrypted local storage

fogvault

0.1.0 ↗

Released

An independently versioned Rust vault and browser SDK for encrypted persistence, locking, backups, and recovery.

Initial release Native SQLite storage and browser Worker/IndexedDB adapters, with encrypted backup transport.

Use the Python library and workflows

datafog Python

4.12.0 ↗

Released

The Python library, CLI, and workflow integrations, including a LiteLLM guardrail. Versioned separately from the Core SDK.

In this release Structured detection across engines, plus improved nested tool-argument and streamed-response handling in LiteLLM.

Coming soon

datafog for Chrome

Local protection in your browser. The Chrome extension processes scanned content on your device.

Chrome extension privacy policy →
Detection is the beginning

Choose what happens
to sensitive data.

Different workflows need different protections. Select the information to transform, apply rules by entity type, and exempt approved values.

Redact · Mask · Remove

Remove what you don’t need.

Replace sensitive values with typed placeholders, mask them with optional partial visibility, or remove them from the text.

Explore transformations ↗

Pseudonymize

Preserve useful relationships.

Use keyed pseudonymization when repeated values need consistent replacements. Your application supplies the key provider.

Understand pseudonymization ↗

Tokenize · Restore

Restore when authorized.

Use provider-backed tokenization for reversible replacements. Your provider owns storage and authorization; Core checks the request scope.

See tokenization and restoration ↗

Redaction, masking, and removal work across all SDKs. Pseudonymization and tokenization use application-supplied providers in Rust, Python, and Node.js.

Build with datafog

Start in the runtime
you already use.

Scan for findings, transform selected values, or combine both in one operation. The same Core defines the privacy behavior across SDKs.

Installation guide ↗

Already using the datafog Python package? Core has a separate package and API. Follow the migration guide.

# pip install datafog-core
from datafog_core import scan_and_transform

result = scan_and_transform(
    "Contact ada@example.invalid",
    {"transform": {"default": {"strategy": "redact"}}},
)
print(result.text)
# Contact [EMAIL]
More tools & integrations

Connect privacy to your workflow.

Explore agent plugins, gateway adapters, and other ways to use datafog. Each has its own setup and availability.

Claude Code plugin · v0.2.1

DataFog for Claude Code

Replace detected personal data and selected credentials with reversible markers in files and tool output. Detection and the encrypted vault stay local. Supported on Apple Silicon macOS and selected Linux x86_64 systems; see coverage and platform limits.

npm release · 0.3.0

fogclaw for OpenClaw

The fogclaw plugin brings PII detection and redaction to OpenClaw.

Explore fogclaw ↗
Also available

datafog API ↗ · Docker distribution for self-hosted HTTP access. datafog Instructor 0.1.0b8 ↗ · An older beta for LLM-based PII extraction; requires an external model API.

Follow development

A shared foundation.
Independent release tracks.

Core provides the detection engine, MCP brings it to local agent workflows, Python adds application integrations, and fogvault provides encrypted persistence. Follow the product you use for its setup, release notes, and supported capabilities.

Available in Core today

Build the protection you need.

  • Text scanning and structured-record protection, including supported person-name fields.
  • SDKs for Rust, Python, Node.js, and browsers.
  • Configurable transformations, with provider-backed operations in server runtimes.

Follow each product

Keep up with what ships.

See the product release highlights ↑ · Follow the Core roadmap ↗

Performance varies by workload. See the 0.3.0 benchmark methodology and results.

Research preview

A small PII model.
Local Rust inference.

We fine-tuned a seven-category PII detector on a Mac and evaluated it on 90,018 held-out synthetic documents. Read the results, what regex still does better, and what remains unproven.

Read the research preview ↗

Bring privacy protection
to your workflow.

Embed the engine, connect your agent, or build encrypted storage. Choose the datafog product that fits.