Protect every action your agent takes.
guardrails prompt-injection data-leakage-prevention llm-safety ai-gateway content-safety ai-agent-security ai-security-gateway enterprise-ai-guardrails openclaw openclaw-security
- Updated
- TypeScript
#
content-safety
Here are 38 public repositories matching this topic...
Review and moderation, your way. Online safety dashboard, queues, routing and automatic enforcement rules, and integrations.
- Updated
- TypeScript
An intelligent task management assistant built with .NET, Next.js, Microsoft Agent Framework, AG-UI protocol, and Azure OpenAI, demonstrating Clean Architecture and autonomous AI agent capabilities
sql-server dotnet nextjs postgresql e2e-tests clean-architecture unit-tests agent-framework ai-agent vitest playright azure-open-ai content-safety ag-ui-protocol
- Updated
- C#
NudeDetect is a Python-based tool for detecting nudity and adult content in images. This project combines the capabilities of the NudeNet library, EasyOCR for text detection, and the Better Profanity library for identifying offensive language in text.
python open-source opencv machine-learning computer-vision deep-learning image-processing image-analysis text-detection profanity-filter adult-content nudity-detection content-moderation ethical-ai nsfw-detection easyocr ai-tools nudenet content-safety better-profanity
- Updated
- Python
A JavaScript-based content safety system designed to detect and filter sensitive media in real-time, ensuring platform compliance and user protection.
- Updated
- JavaScript
Step-by-Step tutorial that teaches you how to use Azure Safety Content - the prebuilt AI service that helps ensure that content sent to user is filtered to safeguard them from risky or undesirable outcomes
- Updated
- Jupyter Notebook
Transform uncertainty into absolute confidence.
javascript microsoft app azure teams net foundry metricas ai-agents rag entra-id content-safety document-intelligence-rag
- Updated
- C#
🔍 Benchmark jailbreak resilience in LLMs with JailBench for clear insights and improved model defenses against jailbreak attempts.
python flask analytics openai alignment model-evaluation ai-safety security-testing red-teaming model-robustness anthropic litellm content-safety llm-jailbreaks tool-calling llm-benchmark ai-evals textual-tui
- Updated
- Python
Benchmark LLM jailbreak resilience across providers with standardized tests, adversarial mode, rich analytics, and a clean Web UI.
python flask analytics openai alignment model-evaluation ai-safety security-testing red-teaming model-robustness prompt-injection anthropic litellm content-safety llm-jailbreaks tool-calling llm-benchmark adversarial-testing ai-evals textual-tui
- Updated
- Python
Technical presentations with hands-on demos
python machine-learning ai jupyter-notebook presentations educational ai-agents azure-ai responsible-ai azure-openai llm prompt-engineering langchain content-safety langgraph
- Updated
- Jupyter Notebook
Production-Grade LLM Alignment Engine (TruthProbe + ADT)
- Updated
- Python
Pre-Publish Security Gate - Scan and redact sensitive information before sharing
- Updated
- Python
A Chrome extension that uses Claude AI to protect users under 18 from inappropriate content by analyzing webpage content in real-time.
nodejs chrome-extension typescript chrome-extensions claude-ai claude-api content-safety claude-3-sonnet
- Updated
- TypeScript
Content moderation (text and image) in a social network demo
- Updated
- C#
The open-source safety stack for AI agents. Policy engine, content scanner, approval workflows, audit trails. 924+ tests. MIT licensed.
open-source security typescript mcp owasp authorization ai-safety human-in-the-loop policy-engine ai-agents audit-trail guardrails ai-agent prompt-injection content-safety agentic-ai eu-ai-act mcp-server mcp-security agent-safety
- Updated
- TypeScript
Responsible AI toolkit for LLM applications: PII/PHI redaction, prompt injection detection, bias scoring, content safety filters, and output validation. Framework-agnostic Python library with FastAPI demo.
python compliance hipaa gdpr bias-detection fastapi guardrails responsible-ai pii-redaction llm prompt-injection content-safety
- Updated
- Python
Study Buddy is a user-friendly AI-powered web app that helps students generate safe, factual study notes and Q&A on any topic. It features user accounts, study history, and strong content safety filters—making learning interactive and secure.
- Updated
- HTML
Content safety evaluator built on OpenAI's gpt-oss-safeguard-20b — zero dependencies, streamed verdicts, editable policies
- Updated
- HTML
profanity checker text moderation
python scraper checker text-processing profanity profanity-filter content-moderation text-sanitization content-safety
- Updated
Public app demo showing LLOYD working with GPT-2.
ai-safety interpretability tone-analysis drift-detection guardrails streamlit content-safety semantic-drift
- Updated
Improve this page
Add a description, image, and links to the content-safety topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the content-safety topic, visit your repo's landing page and select "manage topics."