Artificial Intelligence1 min read

Securing third-party AI agents on Red Hat AI with OpenShell

By · Published by Everything Blog

In short

The new architecture leverages Omnigent as a unified interface to run tools such as Claude Code, Codex, Pi, and Goose interchangeably without code rewrites. Administrators prepare the environment on Red Hat OpenShift by constructing custom Universal Base Image sandboxes governed by OpenShell policies. OpenShell profiles standardize credential injection across external services like OpenAI, LiteMaaS, and GitHub. Furthermore, the deployment integrates with Keycloak authentication and uses custom Kustomization overlays to let teams save, fork, and share active sessions.

Key points

  • Standardized OpenShell profiles streamline credential injection and policy governance acr…: Standardized OpenShell profiles streamline credential injection and policy governance across diverse providers like GitHub, LiteMaaS, and OpenAI.
  • Organizations can deploy the system to Red Hat OpenShift using Kustomization overlays int…: Organizations can deploy the system to Red Hat OpenShift using Kustomization overlays integrated with Keycloak authentication.
  • Running Omnigent in server mode enables real-time collaboration, allowing team members to…: Running Omnigent in server mode enables real-time collaboration, allowing team members to save, share, and fork live agent sessions.

Sources checked by our analysis pipeline: 1

The AgentOps strategy in Red Hat AI 3.6 is bring your own agent (BYOA), providing a sandbox environment for running agent harnesses through the addition of the OpenShell open source project.

In this article, I demonstrate the Omnigent project, a "meta-harness" for AI agents that gives a common UI layer over Claude Code, Codex, Pi, Goose, and others. You can swap or combine harnesses without rewrites, keep them in check with policies and sandboxing, and collaborate in real time on the same live session, from any device.

Omnigent can work in server mode so session data can be saved, shared between team members and forked, while preserving access to the underlying agent. Figure 1 provides an overview of the architecture.

Implementation

While Omnigent can work with many sandbox providers, this article focuses on running it through OpenShell on Red Hat OpenShift to take advantage of BYOA. The documented path for Omnigent on OpenShell gives a basic integration, but for Red Hat OpenShift extra steps are needed. You can follow along with this exercise by implementing everything in my example GitHub…

Artificial Intelligence