I started building Spider as an experiment to see how far AI agents could go in autonomous security research.
What began as a personal project turned into a multi-agent system that can coordinate reconnaissance, OSINT, vulnerability analysis, and deterministic finding validation through Claude Code.
My goal was to reduce manual work and make AI-driven security research more reliable, especially when it comes to false positives.
Multi-agent AI system that turns Claude Code into an autonomous pentest red-team lead. Recon, exploitation, OSINT and submission-ready reporting with deterministic oracles and zero false positives
