About Ryvx

Autonomous AI penetration testing

Ryvx runs autonomous LLM agents that recon a target, hunt for vulnerabilities, validate each one with a working proof-of-concept, CVSS-score it, and suggest a concrete code fix — for source code, local apps, live URLs you're authorized to test, or a whole bug bounty program's scope.

The actual bet isn't "more autonomous than the next tool." It's three things held together: every finding is gated behind a working exploit, not an unconfirmed suspicion; every exploit against a production-tagged target needs a live human to say yes first; and every tool call any agent makes is written to an append-only audit log, so a scan's actions can be defended after the fact.

What it refuses to do

Two rules don't bend. Ryvx will not report a finding without a working proof-of-concept — the tool that files findings hard-rejects anything without one, "PoC or it didn't happen." And it will not run an exploit against a production-tagged target without a human approving it first; run non-interactively, it auto-denies rather than silently proceeding or hanging.

Where it came from

Ryvx started as research into Strix, an existing open-source agentic pentester, and the core architecture — a root orchestrator that never touches the target itself, a subagent graph that does the actual work, PoC-gated reporting, CVSS scoring — is deliberately close to it. Everything past that point is Ryvx's own: the human approval gate, the audit trail, cost budgeting, bug bounty scope mode, and the dashboard.

What's proven, and what only compiles

A tool built around "PoC or it didn't happen" should hold its own claims to the same standard, so we publish what we haven't verified as readily as what we have. A capability audit checks every area against the actual code rather than the plan: most modules pass their own self-check and the automated smoke suite is green, but "passes its tests" and "has worked for a real user" are different claims. Several pieces — the ticket-tracker integrations, the entire hosted/billing path, one reverse-engineering tier, bug bounty scope mode — are finished and tested but have never been run against anything real yet.

The clearest example: we published benchmark recall numbers against known vulnerable apps, then withdrew them. An internal audit found every run behind those numbers had been cut short before its agents finished investigating, so the scores were floors, not measurements — and in at least one case, the credited and missed findings didn't even match what that run had actually produced. They stay withdrawn until a complete, untruncated run exists, and whatever replaces them will be generated from that run's own artifacts rather than written by hand.

Contact

Questions about the product: ryvx.pentesting@gmail.com