Content Moderation Python Packages

pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

200K 74 10

pydantic-ai-middleware

55K 74 10

matcher-py

A high-performance matcher designed to solve LOGICAL and TEXT VARIATIONS problems in word matching, implemented in Rust.

23K 19 1

glin-profanity

Open-source ML-powered profanity filter with TensorFlow.js toxicity detection, leetspeak & Unicode obfuscation resistance. 21M+ ops/sec, 23 languages, React hooks, LRU caching. npm & PyPI.

4K 53 9

pytector

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, and LangChain guardrails.

4K 44 24

lexicont

Policy-driven agent for real-time text moderation

3K 1 1

anthale

Anthale's official Python SDK

1K 1 0

forcefield

ForceField Python SDK -- AI security in 3 lines of code. Prompt injection detection, PII redaction, security evals, tool governance. GitHub Action, pre-commit hook, Homebrew, VS Code extension.

1K 1 0

guardrailprobe

Stop testing your model. Test your guardrail layer. guardrailprobe fires 78 OWASP LLM Top 10 attack probes across 11 backends — Lakera, NeMo, Presidio, Azure Content Safety, Bedrock Guardrails, LLM Guard, and five more — and outputs signed PDF and JSON comparison reports.

1K 0 0

toxic-detection

Intelligent AI Agent for Real-time Content Moderation 97.5% accuracy | Multi-stage ML pipeline | Production-ready Zero-tier filtering + Embeddings + Fine-tuned BERT + RAG

1K 1 0

badwords-py

High-performance profanity filter

1K 13 3

ai-provenance-tracker

Open-source multimodal AI provenance detection platform with explainable evidence cards, provider consensus, and benchmark-driven quality gates.

816 3 1

moderators

One package to moderate them all

419 7 0

llm-medical-guard

Guardrails for LLM-generated medical and health content

400 0 0

llama-index-forcefield

LlamaIndex integration for ForceField AI security -- scan prompts and moderate outputs in your LlamaIndex pipeline.

349 1 0

langchain-forcefield

LangChain integration for ForceField AI security -- scan prompts and moderate outputs in your LangChain pipeline.

284 1 0

siftfy

Official Python client for the Siftfy spam-classification API.

267 0 0

shantay

Trying to make sense of the EU's DSA Transparency DB

263 3 1

openscenesense

OpenSceneSense is a Python library that harnesses AI for advanced video analysis, offering customizable frame and audio insights for dynamic applications in media, education, and content moderation.

253 25 1