Skip to content
APG · PreventionAgent Policy Governance
Policy-as-code

Lyra

Agent policy-as-code

The capability-brokered, information-flow-aware policy engine.

Get your Agent Exposure ReportHow the platform works
What it does

One policy language and one signed audit log govern what every agent may do: which tools, MCP servers, models, data, and egress. Written once, enforced at the endpoint by Beacon and across the mesh.

  • Capability-brokered, information-flow-aware policy-as-code.
  • Authored once; enforced deterministically at the endpoint, no cloud round-trip.
  • One signed audit chain covers OWASP ASI and NIST AI RMF / ISO 42001 alike.
Where it fits

One module of the Alyria platform.

Lyra works alongside the rest of Alyria — prevention and detection for every AI agent your people run, tied together by one policy engine and one signed audit chain.

BeaconNode agentObservatoryCloud consoleConstellationMesh + shared memorySpectraTelemetryUmbraAgent secrets
See how the whole platform fits together

Put Lyra to work.

Deploy Beacon read-only and see how Lyra fits at the endpoint, under your keys.

Get your Agent Exposure ReportHow the platform works