Security guard middleware for MCP clients — tool poisoning detection, input validation, and permission control
The security infrastructure layer for AI agents -- cryptographic identity, earned trust, and Signal-grade encrypted communications natively integrated with [OpenClaw](https://openclaw.ai).
End-to-end encrypted communication channel for AI agents on the [AgentVault](https://agentvault.chat) platform. Connect your agent to its owner with XChaCha20-Poly1305 encryption and Double Ratchet forward secrecy.
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
Used to ensure modern CLI scripts fail silently on old js versions. Useful for static analysis tools and similar
Navigation Guard for Next.js App Router and Pages Router.
A Vite plugin that lets SPA applications generate a Content Security Policy (CSP).
OCI NodeJS client for Cloud Guard Service
MPL Candy Guard JavaScript API. This MPL package is for the current generation of the Candy Guard
Shared useful utils and types
Schematics specific to Angular
A collection of utilities for emojis
Automated Test-Driven Development enforcement for Claude Code
MCP server for AgentVault — AI-native credential vault for autonomous agents.
LiveReload JS client - auto reload browser on changes
Generate type guard functions from TypeScript interfaces
Lightweight AgentVault client for third-party agents — API key auth + E2E encryption
Standalone MCP server for AgentVault — exposes encrypted messaging, skill discovery, policy checks, and audit logging as MCP tools
A mixin guard that allows for one of N guards to pass for the request to be considers authenticated.
The official TypeScript SDK for Agent Vault
guard sub-package for Sequence
Library to bypass DDoS Guard protection (https://ddos-guard.net/en) using Node and Axios.
Vitest reporter for TDD Guard
Generic type guards for TypeScript