ZeroQuarry
Mine your 0-days before someone else does.
ZeroQuarry is an AI-powered offensive security platform that uses an adversarial multi-agent loop to find vulnerabilities across source code, compiled binaries, and live cloud assets. A red-team agent attempts to prove exploitability while a vendor-team agent challenges each finding, filtering out false positives before they reach developers. Each confirmed finding ships with a CVSS-style score, a reproducible proof-of-concept, and a drafted patch diff ready to review and merge.
Two adversarial AI agents — a red-team attacker and a vendor-team defender — debate each potential finding across source code, binaries, and live assets; only proven, contested findings with working PoCs and patch diffs reach the user.
security engineers and development teams that ship software
Background.
- Status
- launched
- Business model
- unknown
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.