Search Packages

presidio-analyzer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-anonymizer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

datafog

Python SDK for PII detection and redaction in text and images, combining regex + NLP pipelines for production privacy workflows.

presidio-image-redactor

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-structured

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

doc-redaction

Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface. Demo: https://huggingface.co/spaces/seanpedrickcase/document_redaction or with try with VLMs: https://huggingface.co/spaces/seanpedrickcase/document_redaction_vlm

stateloom

The control plane for AI agents. Track, secure, and optimize every agent run.

pii-codex

A research python package for detecting, categorizing, and assessing the severity of personal identifiable information (PII)

veritensor

Antivirus for the AI Supply Chain. Scans models, datasets, notebooks, and RAG documents for threats.

zetro-sentinel-sdk

Python SDK for AI Sentinel - The Firewall for AI Agents. Protect against prompt injection, data leaks, and unauthorized tool execution.

jpi-guard

Python SDK for jpi-guard — Japanese prompt injection detection API

agentarmor

The full-stack safety layer for AI agents. Budget limits, prompt injection shields, PII filtering, output firewalls, and hooks — in 2 lines of code.

llm-safe-pl

[DEPRECATED — use pii-toolkit] Reversible Polish PII anonymization for LLM workflows. Successor packages: pii-veil, pii-core, pii-presidio.

protegrity-developer-python

Protegrity AI Developer Edition – Python SDK for Data Discovery and Protection APIs

forcefield

Zero-dependency AI security library -- prompt-injection detection, PII redaction, content safety, rate limiting, abuse detection, tool governance, and security evals for LLMs in 3 lines of Python.

metadata-guardian

Provide an easy way with Python to protect your data sources by searching its metadata. 🛡️

mh-gdpr-ai

Your LLM prompt has a name in it. It just crossed the Atlantic. That's a GDPR violation. This fixes it in 3 lines.

datacruxai

Lightweight CPU-only data quality toolkit for LLM instruction tuning datasets.

electripy-studio

Production-grade Python toolkit for AI product engineering — LLM gateway, policy guardrails, RAG eval, agent collaboration, telemetry, and more.

vllm-sr-sim

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

privacy-mask

Automatically redacts sensitive data in screenshots before sending to AI agents

wonderwallai

WonderwallAi — Open-source AI firewall SDK for LLM applications. Prompt injection detection, semantic topic enforcement, PII filtering, canary tokens, file sanitisation. pip install wonderwallai.