AI Manipulation Defense System (AIMDS) with self-learning, prompt injection detection, and vector search integration

Dependency injection support for fastify framework

LiftrBase TypeSpec library

NodeJS package for generating realistic browser-like HTTP headers.

<p align="center"> <img src="./website/public/og.png" /> </p>

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Sentry Bundler Plugins

Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injection, credential/env exfiltration into LLM-visible output, over-broad filesystem/tool scope and dynamic eval before you wire a server i

An extension to Aurelia's DI container which supports injection into properties.

Run commands concurrently

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

NestJS integration for redlock-universal - Distributed Redis and Valkey locks with decorators, modules, and dependency injection

Core services related to interacting with Sinch API

---

Dependency injection utilities for Angular

An fast implementation of a generative bayesian network.

No description provided.

easily create complex multi-column command-line-interfaces

NodeJS package for generating realistic browser fingerprints.

AgentsAegis security training package. This is a safe, empty package used for trap command injection training. See https://agentsaegis.com