Live Demo: Runtime Behavioral Monitor

Four real scenarios below, computed once from dense-armor's actual detectors (classify_segments + cusum_detector + one_sided_upper_filter, radius=5, ref_mult=2 -- the same call you'd make yourself) against the real telemetry of a Qwen2 1.8B agent (via Ollama), not synthetic noise -- see test/agent_v2/ for how it was generated. Pick a scenario; the red points are exactly what the library flagged, nothing hand-picked.

Normal Transient glitch Persistent drift Legitimate task switch

---

What this does not show: whether Dense-Armor catches a security attack, not just a timing anomaly. It does not -- a real indirect prompt injection against the same agent succeeded 10/10 times and was flagged 0/10 times by this exact detector stack. See Experiment 40 for that real, honest negative result. Dense-Armor is a runtime behavioral-drift/glitch monitor, not a semantic security layer.

Have an agent in production with this problem? Open a GitHub Discussion -- two things worth knowing: does your pipeline have silent drift/glitches today, and what would you actually want a runtime monitor like this to catch that isn't shown above?

pip install dense-armor

from dense_armor.utility.arbiter import classify_segments
from dense_armor.utility.cusum import cusum_detector
from dense_armor.utility.one_sided import one_sided_upper_filter