Libraries tagged by AI Safety

AI Guardrails Prompt Safety recipe for the Drupal AI module. Installs guardrails to block injection attacks, XSS patterns, and liability-triggering topics such as legal advice, medical advice, and sensitive subjects.

Go to Download

Deterministic prompt-injection guardrails for laravel/ai: tool firewall, input screening + injection audit, untrusted-output sanitization, and a HITL approval bridge.

Go to Download

Bundles the complete AI safety stack for Varbase: Prompt Safety Liability set, Prompt Safety Security set, PII Protection set, AI Logging with 90-day retention, and AI Observability.

Go to Download

Pre-populates starter context items (Brand & Identity Guidelines, AI Editorial Rules, AI Safety Guardrails) for every Varbase site via the Context Control Center (CCC) module.

Go to Download

Blocks image uploads to Media: Image that contain nudity, sexually suggestive content, gore, graphic violence, or graphic medical imagery. Uses AI Validations and any vision-capable AI provider.

Go to Download

Standalone Laravel package for evidence-tier labeling and risk review guardrails.

Go to Download

Netresearch AI skill for PHP 8.x modernization, type safety and legacy code upgrades

Go to Download

One file. Zero commands. Makes Claude smart about your codebase. Any language. Any framework.

Go to Download

Symfony bundle for Google Perspective API - AI-powered content moderation with flexible threshold management, caching support, and multiple usage patterns. Modern alternative to abandoned wrappers.

Go to Download

Enterprise-grade input/output safety & compliance layer for AI agents.

Go to Download

Agent Orchestration in your web app. Bring Claude Code into your Laravel app — no terminal hopping, no context copying. Orca turns every page into a live coding session: full page awareness, screenshots on demand, plan-then-execute safety, and seamless pop-out to macOS Terminal.

Go to Download

A modern PHP client for the Hugging Face Inference API with full type safety and comprehensive model support

Go to Download

Shared AI infrastructure for Toweringmedia Magento 2 extensions: one place to configure OpenAI-compatible providers, Google Gemini, Whisper STT, TTS, embeddings, agent runtime, conversation memory, daily call budgets, and production safety gates — so Nora AI, Search Intelligence, and Product Builder stay focused on merchant workflows instead of re-implementing AI plumbing.

Go to Download

PHP SDK for the Wardstone LLM security API. Detect prompt injection, content violations, data leakage, and unknown links.

Go to Download

Input/output safety layer for PHP LLM apps: PII redaction, prompt-injection detection, secret scanning, and content moderation as a composable pipeline.

Go to Download