CPEX Documentation#

CPEX is a policy enforcement runtime for AI agents: a deterministic reference monitor that mediates every operation an untrusted LLM triggers. It runs a policy-defined security pipeline per operation (authorization, delegation, redaction, information-flow control, audit), written in APL (Authorization Policy Language) and attached to each capability an agent can invoke.

Start with the Vision for the reference-monitor model, the Quick Start to stand up an enforcement point, or APL to write policy.

Using the Python 0.1.x line? Its docs are preserved under 0.1.x (Legacy).