Privacy Compliant Data Collection With Configurable Masking

via “pii masking and data privacy enforcement”

Open-source AI observability with conversation replay and user tracking.

Unique: Applies pattern-based PII masking at ingestion time before data is persisted, ensuring sensitive information never reaches Lunary's storage, with configurable rules for domain-specific data types

vs others: More privacy-preserving than post-hoc anonymization because it masks data before storage rather than after, reducing the window of exposure and ensuring compliance by design

via “request/response logging with sensitive data masking”

** - Enterprise MCP gateway with SSO, RBAC, audit trails, and token vaults for secure, centralized AI agent access control. Deploy via Helm charts on-premise or in your cloud. [webrix.ai](https://webrix.ai)

Unique: Implements automatic sensitive data masking in request/response logs based on configurable patterns, enabling detailed debugging without exposing API keys, passwords, or PII, with support for structured logging and external logging systems

vs others: More secure than unmasked logging (prevents accidental secret exposure) and more flexible than tool-level logging (supports centralized masking policies), enabling compliance with data protection regulations without tool code changes

via “pii-masking-with-context-preservation”

A zero-trust SDK for anonymizing PII locally before sending prompts to LLMs and seamlessly rehydrating the response.

Unique: Implements multiple masking strategies (full replacement, partial masking, format-preserving encryption) that enable fine-grained control over privacy/utility tradeoffs, allowing users to preserve just enough context for the LLM to be useful while protecting sensitive data. Provides metadata about which properties were preserved, enabling informed decisions about privacy risks.

vs others: Unlike simple token replacement that loses all context, rehydra's context-preserving masking enables the LLM to understand data types and relationships while hiding actual values. Format-preserving encryption provides stronger privacy guarantees than partial masking while maintaining more utility than full anonymization.

via “privacy-preserving memory storage with optional de-identification”

This package contains the code for training a memory-augmented GPT model on patient data. Please note that this is not the 'letta' company project with thehttps://github.com/letta-ai/letta; for use of their package, plsuse 'pymemgpt' instead.

Unique: Implements privacy controls as first-class memory operations rather than external post-processing; supports configurable de-identification policies that preserve clinical utility while protecting PII

vs others: More integrated than bolted-on privacy layers; privacy policies are enforced at memory storage level rather than just at query time

via “zero-data-collection-privacy-model”

One click to curate AI chatbot, including ChatGPT, Google Bard to improve AI responses.

Unique: Implements a zero-collection privacy model by design, storing all data locally in Chrome extension storage and transmitting nothing to external servers, sacrificing analytics and cloud features for complete user privacy.

vs others: More private than cloud-based prompt managers because no data leaves the browser, but less convenient because there is no cross-device sync, backup, or cloud recovery.

via “privacy-compliant data collection with configurable masking”

Unique: Provides configurable pattern-based PII masking for session replays and event logs, combined with consent management and audit logging. Allows teams to define custom sensitive data patterns beyond standard PII (passwords, credit cards) to mask domain-specific sensitive fields.

vs others: More privacy-focused than Hotjar because it defaults to masking sensitive data and provides granular consent controls; more compliant than basic analytics tools because it includes audit logging and data retention policies.

via “dynamic-data-masking”

via “pii-masking-configuration”

via “sensitive-attribute-masking”

via “sensitive data masking and anonymization”

via “automated data masking and redaction for model training”

Unique: Integrates masking at the data loader level (before model training) rather than post-hoc, preventing sensitive data from ever entering model memory or checkpoints, and supports dynamic masking rules that vary by user role or data sensitivity classification

vs others: More comprehensive than generic data masking tools (Tonic, Gretel) because it understands ML-specific threat models (model extraction, weight inspection) and applies masking at training time rather than only in data warehouses

via “granular privacy control application”

via “pii-stripping conversation masking”

via “pattern-based pii detection and masking”

Unique: Implements client-side pattern-based PII detection with local token mapping rather than relying on server-side redaction, allowing users to maintain control over sensitive data without transmitting raw PII to any external system. The masking occurs in the browser before ChatGPT API calls, creating a privacy boundary at the point of transmission.

vs others: Simpler and faster than manual redaction workflows, but weaker than cryptographic encryption or differential privacy approaches because masking is deterministic and reversible, making it vulnerable to inference attacks if the token mapping is exposed.

via “pii-detection-and-masking”

via “data masking and transformation for test scenarios”

via “access control and role-based data masking”

Unique: Attribute-based access control (ABAC) that evaluates policies at query time rather than pre-computing masked datasets, enabling dynamic policy changes without data reprocessing. Supports multiple masking strategies (tokenization, hashing, partial redaction) applied conditionally based on role attributes.

vs others: More flexible than role-based access control (RBAC) alone because it can express complex policies like 'show full SSN only to HR and compliance, show last 4 digits to managers, redact entirely for contractors.' Faster than row-level security in databases because policies are evaluated centrally rather than distributed across database engines.

via “privacy-preserving local processing with optional cloud sync”

via “sensitive data classification and masking”