CPEX Documentation#

CPEX is a policy enforcement runtime for AI agents: a deterministic reference monitor that mediates every operation an untrusted LLM triggers. Each capability an agent can invoke defines its own enforcement pipeline (authorization, delegation, redaction, information-flow control, audit), configured in APL and run deterministically at the boundary.

Start with the Vision for the reference-monitor model, the Threat Model for what CPEX defends against at each placement, or the Use Cases for the controls running end-to-end behind a real gateway. Then the Quick Start stands up an enforcement point, and APL is where you write policy. Prefer to learn by doing? The Tutorial builds a working enforcement point one capability at a time, with runnable code you can edit and re-run.

Configuring a deployment? Configuration covers the document, Builtins the bundled plugins and the HTTP transport, HTTP Routing and Header Assertions the generic HTTP path, Auditing the decision and effect records, and the Crate Map what each crate holds. Upgrading from 0.2.x? Start with Migrating to 0.3.

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