Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.

Your AI Chief of Staff — Personal Assistant framework for Claude Code. Email, semantic memory, task management, content security. Works standalone or on AI Maestro.

Multi-platform messaging gateways for AI Maestro — connect AI agents to Discord, Slack, Email & WhatsApp. Prompt injection defense, content security, trust-based access control. TypeScript + Docker.

🛡️An AI-powered data governance agent platform. Supports Real-time Interception & Database Batch Cleaning for sensitive info (PII) and spam. Features configurable policies, dual-engine detection (Rule+LLM), and safe write-back with rollback. 🛡️ DataSentry：基于 AI 的全链路数据治理 Agent 平台。支持实时 API 拦截与数据库存量清洗（PII/垃圾信息）。融合“规则+大模型”双引擎检测，提供可配置策略、全链路审计及安全回滚机制。

AI platform fingerprinting digital media via visual & audio analysis to detect and track unauthorized content usage.

A highly optimized, thread-safe, zero-latency streaming text interceptor and sensitive words filter for LLM outputs. Supports Python dicts, raw text, and OpenAI SSE streams out-of-the-box. 专为大模型（LLM）流式输出设计的高性能、线程安全、零延迟文本拦截器与敏感词过滤清洗工具。支持原始文本、Python字典、以及 OpenAI SSE 流。

Local-first security middleware for MCP servers. Content scanning, prompt-injection defence, trust boundaries, manifest integrity, and audit trails. No API keys, no telemetry. OWASP MCP Top 10 aligned.

Scan web content for prompt injection, hidden instructions, and adversarial content targeting AI agents

CreatorShield — AI-powered digital asset protection platform. Invisible steganographic watermarking, automated web-wide infringement detection via Google Cloud Vision, and one-tap Gemini-drafted DMCA takedown notices. Built with Next.js, Clerk, Neon DB, and Cloudinary.

Extension Chrome MV3 de détection de contenus générés par IA (texte, images, vidéos, audio). Heuristiques locales, APIs externes optionnelles, signalement communautaire et inspection HTML/sécurité.