What is DocSanitizer

DocSanitizer is a privacy-first application designed to prepare documents for AI interaction. It works by cleaning sensitive data from files and optimizing the text to save space when sending it to artificial intelligence models. The tool is built on a native Rust engine and operates entirely offline. This means no data ever leaves the user's device. Whether used as a web-based tool or a desktop application, DocSanitizer guarantees zero cloud telemetry, zero network calls, and zero tracking.

Benefits

DocSanitizer offers several key advantages for users who value their privacy and efficiency.

First, it ensures complete data security. All operations happen in transient RAM on the user's computer. No text or metadata is sent to external cloud servers. This protects personal information from potential leaks.

Second, it provides powerful AI scanning. The tool uses an on-device model to detect and censor person names across unstructured text. This runs locally without needing any cloud API calls.

Third, it handles a wide range of sensitive information. The free version redacts emails, phone numbers, drug codes, and medical diagnosis codes. The Pro version adds support for credit cards, Social Security numbers, bank account numbers, and API keys. Users can also choose to keep only the last four digits of sensitive numbers.

Fourth, it optimizes token usage. The tool counts tokens using tiktoken BPE counting on the device. It collapses whitespace and repairs line breaks. This can cut token size by up to 50%, allowing users to process more content within AI limits.

Fifth, it supports many file formats. DocSanitizer processes PDFs, Word documents, spreadsheets, EPUBs, HTML files, plain text, and images via hardware-accelerated on-device OCR.

Use Cases

DocSanitizer is useful for anyone who needs to share documents with AI tools like ChatGPT, Claude, or NotebookLM.

Researchers and students can use it to clean up academic papers before pasting them into an AI chatbot. This ensures no private student IDs or names are accidentally shared.

Legal professionals can sanitize court documents or case files. The tool can redact names and case numbers while keeping the relevant text intact.

Healthcare workers can process patient records. It can remove names and medical record numbers while preserving the clinical notes needed for analysis.

Developers can clean up code repositories or configuration files. The Pro version can detect and redact API keys and secrets before they are shared with an AI assistant.

Anyone working with long documents can use the auto-chunking feature. This splits long files into smaller sections with clear labels, making them easier for AI models to understand.

Pricing

DocSanitizer offers a free tier and a Pro tier.

The Free Tier costs $0 forever. It allows users to process five files per day with a limit of 15 pages per file. It includes header and footer stripping and basic redaction for emails, phone numbers, drug codes, and medical codes. It also includes on-device token counting.

The Pro Tier costs $14.99 per year or $29.99 for a lifetime license. It removes all limits on files and pages. It adds AI Deep Scan for person names, deep PII redaction for financial and legal IDs, a pattern library for custom rules, and a privacy audit report. It also includes reversible pseudonyms and smart auto-chunking for long documents.

Vibes

DocSanitizer has received positive attention for its commitment to privacy. Users appreciate that the tool works offline and does not track their activity. The ability to generate a privacy audit report on the device gives users confidence that their data remains secure. The free tier is seen as a generous starting point for those who want to test the tool without risk. The Pro features are valued by professionals who need to handle large volumes of sensitive data regularly.

Additional Information

DocSanitizer is available as a native desktop app for macOS, Windows, and Linux. It also has a browser-based web app that offers the same privacy and functionality without requiring installation. Native iOS and Android apps are coming soon to the App Store and Google Play. The desktop app supports a global hotkey for instant sanitization and works in offline mode with zero network calls.