Real-time behavioral monitoring for AI agents.
Know when agents go off-baseline. Before they cause damage. Per-agent behavioral baselines with statistical anomaly detection.
npm install @authensor/sentinelCopyimport { SentinelEngine } from '@authensor/sentinel';
const sentinel = new SentinelEngine();
// Record agent actions — baselines build automatically
sentinel.record({ agentId: 'agent-1', action: 'file.read', latencyMs: 12 });
// Check for anomalies
const alerts = sentinel.check('agent-1');
if (alerts.length > 0) {
// Agent behavior has deviated from baseline
alerts.forEach(a => console.warn(a.type, a.message));
}Statistical baselines that adapt to each agent. No thresholds to hand-tune, no ML models to train.
Exponentially Weighted Moving Average
Tracks rolling agent behavior with configurable sensitivity. Recent actions weigh more heavily, so baselines adapt naturally while still catching sudden deviations.
Cumulative Sum
Detects persistent shifts in agent behavior patterns. Small, sustained changes that EWMA might miss accumulate until CUSUM triggers an alert.
Delegation depth monitoring
Alerts when agent delegation chains exceed safe depths. Prevents runaway recursion where Agent A calls Agent B calls Agent C into unbounded loops.
Sub-agent spawn monitoring
Flags when one agent spawns too many sub-agents simultaneously. Catches delegation storms before they cascade into uncontrollable parallel execution.
Agent suddenly hitting policy denials at 10x baseline rate
Agent taking unusually long per action, possible data exfiltration
Agent making far more requests than its established baseline
Cascading agent-to-agent calls spiraling beyond safe thresholds