peertube-plugin-german-ai-mod

Local AI moderation for German comments using ml6team DistilBERT and deepset BERT models

v0.3.7 URL: https://unpkg.com/peertube-plugin-german-ai-mod@0.3.7/main.js

Open Browse Files

peertube plugin moderation ai german hate-speech toxicity bert

@dooor-ai/toolkit

Guards, Evals & Observability for AI applications - works seamlessly with LangChain/LangGraph

v0.1.58 URL: https://unpkg.com/@dooor-ai/toolkit@0.1.58/dist/index.js

Open Browse Files

ai llm langchain langgraph guards guardrails evaluation observability prompt-injection toxicity rag

llm-guard

A TypeScript library for validating and securing LLM prompts

v0.1.8 URL: https://unpkg.com/llm-guard@0.1.8/dist/index.js

Open Browse Files

llm security validation prompt jailbreak pii toxicity profanity prompt-injection relevance

@ethicalzen/sdk

Official EthicalZen SDK for Node.js - AI safety guardrails made simple

v0.1.1 URL: https://unpkg.com/@ethicalzen/sdk@0.1.1/dist/index.js

Open Browse Files

ai safety guardrails llm compliance pii hallucination toxicity ethicalzen

@llm-dev-ops/shield-cli

Command-line interface for LLM Shield - Enterprise-grade security scanning for Large Language Models

v1.0.0 URL: https://unpkg.com/@llm-dev-ops/shield-cli@1.0.0/dist/index.js

Open Browse Files

llm security cli prompt-injection toxicity ai-security content-moderation pii-detection secrets-detection llm-guard