Aegis – post-quantum cyberdefense proxy (687 attacks, 0 breaches, 40d)
Nine-layer autonomous defense with NIST post-quantum crypto, but 23 commits feels early for production claims.
Sistema Autónomo de Ciberdefensa Post-Cuántica
Python proxy combining NIST post-quantum crypto with nine-layer active defense and containment.
Security engineers, infrastructure developers, privacy advocates
Cloudflare · Twingate · LibOQS
Nine-layer autonomous defense with NIST post-quantum crypto, but 23 commits feels early for production claims.
The UI turns complex attack chains into an immediately scannable graph with per-path metrics (risk score, time-to-compromise, assets/credentials impacted) — great for threat modeling and tabletop drills. Feels more like a very polished BAS visualization than a novel research tool; what I want to know next is where the simulation inputs come from (real telemetry, vulnerability feeds, or canned scenarios).
The selling point is sensible: turn individual vulns into chained attack paths so defenders can see realistic breach stories instead of isolated findings. Trouble is, the public surface is a gated sign-in with no demo, examples, or telemetry to judge how it models attacker tradeoffs or integrates with scanners and SIEMs. Visually the control-plane login is clean and modern, but the product's differentiation against established attack-simulation vendors is unclear from the page.
Catches .pth injection vectors from the litellm attack when Snyk and Dependabot miss them.
Zero-code LLM firewall; heuristics under 1ms, optional Groq semantic layer.
Stops zero-width Unicode bypasses that break standard PII filters before LLM calls.