Agent Gateway

Govern every AI agent interaction. Verify identity, enforce access policies, and keep every call attributable.

When AI agents scale into production, teams typically rebuild credential handling, access control, and call logging separately for each integration.

Agent Gateway is an intercepting proxy that sits between callers and managed agent backends, applying identity verification, OPA policy enforcement, and observability to every request from one configuration layer, without modifying agent or backend code.

Every call becomes verifiable, governed, and auditable.

Overview→

What Agent Gateway is, how it governs AI agent interactions, and how to adopt it progressively with identity, policy, and observability controls.

Quickstart→

Create a surface, add identity and OPA access control, and monitor traffic through the Agent Gateway dashboard.

Core Concepts→

Concept pages covering the Agent Gateway’s architecture, protocols, identity model, access control, and federation.

Guides→

Step-by-step guides for real configuration and operational tasks in the Agent Gateway.

Reference→

Field-level reference for Agent Gateway surfaces, gateways, trust registries, settings, and operations.

Frequently Asked Questions→

Common questions about protocols and integration, identity and trust, access control, federation and multi-hop routing, configuration, and deployment in Agent Gateway.