Dlp Python Packages

privateai-client

A python client used to interact with the Private AI's API

ferret-scan

Find and redact sensitive data before it leaks — a fast, offline CLI and Go library that detects PII, secrets, and credentials in files and streams, scores them with context-aware confidence, and redacts them format-preserving. Nothing leaves your host.

privyx

AI data privacy gateway: privacy engine + proxy for LLM providers

agentmetry

Local-first flight recorder for AI coding agents. Hash-chained audit trail, MITRE-mapped sequence detection, DLP. Forwards to the SIEM you already run.

dapla-toolbelt-pseudo

Pseudonymization extensions for Dapla Toolbelt

aggrete

An MCP proxy that enforces your code of conduct across connectors. Permission is not need-to-know.

tarja

Detect and mask Brazilian personal identifiers (CPF, CNPJ, CNS, CNJ, título, CNH) in Portuguese text, with check-digit validation. For LGPD work, DLP pipelines, and stripping PII before text reaches an LLM or a RAG index. Apache 2.0, no dependencies.

traceredact

Redact PII & secrets from LLM prompts, agent traces & tool-call args before they hit your logs. Content-based detection (not just key names), CI-gateable, zero data retained.

garita

Impide que datos personales y credenciales entren a tu repositorio: nombres de tu propio padrón, CURP, RFC, CLABE, NSS y secretos. Hook de pre-commit + GitHub Action. Sin dependencias.

agentsweep

Find and redact secrets in AI coding agent histories (Claude Code, and more).

looselips-guard

Stops your coding agent publishing your data to the world — a PreToolUse egress guard for Claude Code and other agent hosts

contextduty

Local-first prompt firewall — stop secrets & PII from reaching AI tools (IDE, git, AI-API proxy, MCP). Built on Microsoft Presidio.

octowatch-mcp

Read-only MCP server for OctoWatch DLP Cloud (Risks, Anomalies, users, activity, productivity, reports and employee monitoring for Cursor, Claude, and VS Code).

strac-mcp-dlp

MCP server for Strac DLP — detect and redact PII, PHI, PCI and secrets before an AI agent sees them.

ai-prompt-sanitizer

Privacy-first prompt sanitization. Fully local. Zero cloud calls. Fast, smart, and built for real-world AI workflows.

tarja-presidio

Detect and mask Brazilian personal identifiers (CPF, CNPJ, CNS, CNJ, título, CNH) in Portuguese text, with check-digit validation. For LGPD work, DLP pipelines, and stripping PII before text reaches an LLM or a RAG index. Apache 2.0, no dependencies.

ceil-dlp

Open-Source DLP for LLMs and Agents that provides Conversational Coherence

crossfire-rules

Regex rule overlap analyzer for DLP, secret scanning, SAST, and IDS tools

mcpaisuite-workspacemcp

Governed, auditable file workspace for AI agents — sandboxed read/write/edit, ripgrep search, checkpoints, DLP. Python lib · CLI · MCP server · FastAPI.

mcp-egress-guard

Policy enforcement proxy for MCP tool calls: detect leaks, block risky actions, redact sensitive payloads, and log every decision.

gitlab-watchman

Finding exposed secrets and personal data in GitLab

vellaveto-sdk

Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.

pleno-dlp

Verify by Default. Unified DLP scanner.

clowk

Catches credentials you paste into an AI coding agent's chat before they reach the model, files them locally, and records where each one came from. Claude Code, Codex, Gemini CLI. Stdlib Python, no dependencies.