Radius attacks the path, proves it, and proves the fix.
Radius is a team of AI agents that attack your environment inside rules you sign, prove which paths reach your critical systems, and attack each path again after you fix it. Every run adds to a knowledge base of your environment. It covers IT, cloud and OT/ICS.
Nine documents per run
Three reports (executive, technical, compliance), each at three levels: the whole run, a single asset, or a single finding.
A safety trail for every action
What was attempted, what was decided, why, and the rules of engagement in force at that moment.
A knowledge base that compounds
Configuration as found, how things connect, what was found before, and what changed since the last run.
Observe
Assets, services, identities and dependencies, including what was never in the inventory. Discovery is passive by default.

Reason
The attack graph ranks each path by what it reaches.
- Every path traced to what it reaches
- Chains that share a hop share a fix
- MITRE ATT&CK technique mapping

Attack, then validate
Radius runs the real chain against your environment, inside the rules you signed, and confirms how far it got. It stops before impact, and every action is logged.

See the platform in action
Real screens from the product, on demo data.

Roll up your whole exposure (assets, critical findings and remediation pace) on one configurable board.
Safe enough for OT/ICS, so safe anywhere.
The controls were built for hardware you cannot reboot, and they apply unchanged everywhere else.
- Passive discovery by default, with active steps authorized asset by asset
- The attack stops before impact, and nothing is written to a controller
- A stop button that works mid-run
- Aligned with the OWASP Autonomous Penetration Testing Standard (APTS)

How you buy it
Two ways in, both complete: a single scoped run, or continuous coverage that watches your surface all year. You supply the AI model key, or we do.
- A single run: fixed scope, fixed price, re-validation included
- Continuous coverage: the run is credited if you continue inside the re-validation window
- Your AI model key or ours: same scope, different price
Frequently Asked Questions
What does Radius remember between runs?
How does Radius differ from a vulnerability scanner?
Is Radius safe to run against production?
Does it simulate attacks?
What standard does Radius follow?
How long does a run take?
Go deeper
Each part of Radius in detail, on its own page.
How a run works
Observe, reason, attack, validate, report, step by step.
Open →What a run delivers
The three reports, the safety trail, scope and price.
Open →Features & integrations
The connectors that ship today, and the webhooks.
Open →Interactive tour
Walk the real product yourself. No signup, no sales call.
Open →See what your domain exposes.
A free external scan: Radius maps your internet-facing assets without exploiting anything, and we send you what it finds.
Get a free external scan