Introducing Aardvark: OpenAI’s agentic security researcher

Practical AI: Tools, Models & Frameworks

What changed

OpenAI introduces Aardvark, an AI-powered security researcher that autonomously finds, validates, and helps fix software vulnerabilities at scale. The system is in private beta—sign up to join early testing.

Why it matters

A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.

How it compares

Related prior coverage to compare against:

  • Introducing CodeMender: an AI agent for code security
  • Scaling security with responsible disclosure
  • OpenAI Codex

Sources