Teleport Debuts Delegated Agentic Identity and LLM Proxy in Beams Public Beta, for Containing Agents in Production Infrastructure

Two foundational identity concepts — controlling the scope of agent roles and constraining what they can access — now have a production implementation in Beams, Teleport's trusted, ephemeral agent runtime

Oakland, California  — June 16, 2026 — Teleport, the AI Infrastructure Identity Company,  announced today the debut of two foundational capabilities of its Agentic Identity Framework in its public beta of Beams: LLM Proxy and Delegated Identity. These represent Teleport's answer to a critical gap in how organizations are currently deploying AI agents — the absence of identity, access control, and audit at the two most consequential points in any agentic workflow: what the agent is instructed to do, and what it is permitted to access.

Much of AI innovation to date has centered on LLM gateways, that is tools that sit in front of model providers to route traffic, manage cost, and log or screen prompts. Controlling agent behavior when it is accessing production infrastructure, however, is largely outside their scope. Teleport's LLM Proxy, in contrast, brings an enforcement layer that is wired into the same identity and zero trust plane that governs privileges and infrastructure resources, such as production databases, cloud APIs, and internal services. 

LLM Proxy: A Control Plane for Agent Behavior

The LLM Proxy sits between an agent and its inference endpoint, giving teams visibility and enforcement at the point where agent behavior originates. Every request and response is inspected and written to Teleport's audit log. This combines with a per-Beam allow list of resources to enforce controls that govern which agents can reach which inference endpoints and under what conditions. The result is enforcement before instructions are ever executed along with a precise, tamper-resistant record of what every agent was told to do. 

Delegated Identity for Least-Privilege Access

Delegated Identity allows a human operator or an agent to define and assign the permissions an agent will carry — defining exactly what infrastructure it is authorized to reach. Rather than inheriting broad credentials or running with standing access, each agent receives a delegated identity with scoped privileges to accomplish a specific task delegated by human or another agent. All activity is recorded, analyzed by peer agents and tied to the identity and task.

This makes least-privilege access a runtime property of every agent. If an agent is compromised or behaves unexpectedly, the blast radius is bounded. Delegated Identity implements zero trust and JIT for agents.

"Delegated identity and LLM Proxy, all parts of Agentic Identity Framework unblock enterprise organizations from deploying agentic workloads interfacing with real infrastructure, making a leap from vibe-coding and prototyping to real production engineering," said Alexander Klizhentas, CTO of Teleport.

LLM Proxy and Delegated Identity are available now in the Beams public beta. Engineers can get started at beams.run.

About Beams

Beams is Teleport's trusted runtime for AI agents. Each Beam runs in an isolated Firecracker VM with built-in identity, connecting agents to infrastructure and inference services without secrets, with full audit from instantiation to termination. Beams is available in public beta at beams.run.

About Teleport

Teleport, the AI Infrastructure Identity Company, prepares organizations for an AI future by delivering a unified identity layer for infrastructure — humans, machines, workloads, and AI agents — that is cryptographically secured. By replacing fragmented identity and access management systems and static credentials with Infrastructure Identity, Teleport scales zero trust across cloud and on-prem environments. This approach prevents identity attacks, accelerates engineering, and secures non-deterministic agentic workflows. For more information, visit goteleport.com or follow @goteleport.