Runtime security for AI agents
Identity, policy enforcement, in-line DLP, human approvals, and append-only audit. Drop it between your agents and everything they call.
Install in one line Linux, macOS, or Windows. The installer generates every secret and brings the stack up in three minutes.
What Lupid is Three things in one product: security on the wire, observability over every action, and full IAM.
Register your first agent From a fresh install to a working policy-enforced agent in under five minutes.
How it works Architecture, network topology, and where each enforcement decision is made.
Write a policy Allow, deny, or escalate to a human approver — per tool, per resource, per agent.
Install with an AI agent Hand a single URL to Claude Code, Cursor, or Cline and have it deploy Lupid for you.