Demo build: every run replays a real captured triage (captured with Claude sonnet, replayed faster than real time). No API key, no backend. Clone the repo to run the live agent.
Skip to content
How to use it & glossary

Guide

How to drive the agent, then a working glossary of the security frameworks and data sources under the hood. Pick a topic from the rail; every entry is deep-linkable.

Start a triage

Open the Triage tab and describe what to assess. The agent selects the tools from the shape of the input; you never wire them by hand. Five accepted inputs:

A CVE IDCVE-2021-44228

The full NVD record plus every operational signal (KEV, EPSS, exploits, patch) fan out in parallel.

A package at a versionlog4j-core 2.14.1

OSV.dev advisories for that exact package and version: the inverse of a CVE lookup.

A natural-language questionIs my Spring app exposed to Spring4Shell?

Semantic search over a local index of recent high-severity CVEs when there is no explicit ID.

An SBOMCycloneDX / SPDX / requirements.txt

Paste it to bulk-triage the most-likely-vulnerable components in one pass.

Nmap XMLnmap -oX scan.xml

Service banners become CVE queries; parsing is XXE-safe (defusedxml, no DTD).

In this hosted demo the Triage tab replays seven real captured runs (model sonnet against the live stack, captured 2026-07-02), covering the full SSVC ladder from Act to Track. Pick one from the example gallery; free-text input matches only those seven (a CVE id from the set works too). Replay pacing is compressed so you are not waiting out the real 35-135 second runs; the waterfall durations shown are the real measured ones. Clone the repo to run the live agent on arbitrary input.

The report streams in node by node as the agent reasons; a single-CVE triage typically settles in under two minutes.

1 / 17Read the SSVC verdict