Skip to main content

What is Behavry

Behavry is an identity-aware policy enforcement platform for AI agents. It sits between autonomous agents and the systems they interact with — authenticating every action, evaluating it against policy, logging it, and either allowing, modifying, or blocking it.

Think of it as Active Directory + UEBA + policy enforcement, purpose-built for autonomous AI agents.

"Runtime telemetry tells you what happened. Behavry tells you whether it should have."


How it works

Every tool call from every agent flows through the Behavry MCP Proxy:

  1. Authenticates the agent (JWT RS256, OAuth 2.1)
  2. Scans the call for DLP violations and inbound injection
  3. Evaluates the call against OPA policy (allow / deny / escalate)
  4. Logs the decision with a tamper-proof hash chain
  5. Monitors behavioral baselines and fires alerts on anomalies

Who it's for

PersonaProblem Behavry solves
CISOsAuditability, compliance evidence, least-privilege enforcement for AI
Security ArchitectsPolicy-as-code for agent behavior, runtime enforcement, SIEM integration
Platform EngineersOne proxy to govern all agents — no per-agent instrumentation
Compliance TeamsPre-mapped controls for SOC 2, ISO 27001, NIST AI RMF, EU AI Act

Key capabilities

CapabilityDescription
Agent IdentityEvery agent gets a cryptographic identity; no anonymous tool calls
Policy EngineOPA with Rego policies — allow, deny, or escalate
DLP Scanner26 outbound patterns; blocks sensitive data before it leaves
Inbound Injection7-class scanner for prompt injection in tool results (AOC-1)
Requester IdentityTraces which entity instructed each action (AOC-3)
Behavioral MonitorPer-agent baselines, anomaly detection, six-dimension risk score
HITL EscalationHuman-in-the-loop approval queue for borderline actions
CompliancePre-mapped to SOC 2, ISO 27001, NIST AI RMF, EU AI Act, GDPR, HIPAA

Quick start

git clone https://github.com/behavry/behavry
cd behavry
make dev # starts backend + OPA + TimescaleDB
make setup # provisions dev agent + applies MCP config

Open the dashboard at http://localhost:5173.

Full local setup guide
Connect your first agent