vincentxuu

Create, update, and verify evidence-aware articles across repositories and Web agents.

Portable, evidence-first multi-source research for tools, frameworks, papers, models, products, and trends.

Threat modeling, secure coding, and severity-classified security review for software and AI-agent changes, grounded in OWASP practice and current agentic-AI trust-boundary research. Auto-adapts its report between a technical findings report and a plain-language, actionable summary for non-technical vibe coders.

Spec-driven software delivery with independent model review, layered verification, and Playwright video evidence.