Chapter 4. Developer Preview features

The Agent Catalog in AI Hub provides a centralized interface for discovering and exploring agent starter kits as a Developer Preview. You can browse available agents, view each agent’s description, and filter by framework or use text search to find agents for a specific use case. Each catalog entry displays the agent’s description, framework, and a README file with additional information about the agent.

The catalog ships pre-loaded with agent starter kits built on LangGraph, CrewAI, LlamaIndex, and other agentic frameworks.

To enable this Developer Preview feature, set the agentsCatalog feature flag to true.

To access the catalog, from the OpenShift AI dashboard, click AI hub Agents.

You can save your Gen AI Studio Playground configuration as a named, reusable agent scoped to your project namespace. A saved agent captures model selection, inference parameters, MLflow prompt references, retrieval augmented generation (RAG) knowledge sources, and Model Context Protocol (MCP) server connections. Agents are stored as Kubernetes resources in the project namespace and are visible to all project members.

Key capabilities:

In OpenShift AI, an external metering IPP plugin and standalone metering service are available as a Developer Preview feature. This feature enables platform operators to track per-user and per-model token consumption, attribute costs, enforce quotas, and generate chargeback reports for inference requests passing through the AI Inference Gateway.

The external-metering plugin operates in the IPP plugin chain. It checks user balances before processing requests and extracts token usage details, such as input, output, cached, cache write, and reasoning tokens, from OpenAI and Anthropic provider responses. The plugin then emits CloudEvents to a standalone metering service backed by PostgreSQL. The service aggregates usage, calculates cache-aware pricing, and provides an administrative dashboard and REST API for usage queries and balance checks.

You can connect Models-as-a-Service (MaaS) inference traffic to an external metering or billing system by using Backend-Based Routing (BBR) plugins. This integration enables platform operators running MaaS as a commercial AI service to capture per-request token usage and enforce token budgets through an external metering system.

The external metering integration includes two BBR plugins:

The File Processors API is available on OGX. The File Processors API allows you to convert documents into vector-ready chunks using the following providers:

You can deploy and manage OpenClaw, an open-source general-purpose agent, on Red Hat OpenShift AI. The starter kit includes validated Kustomize manifests and an automated installer to manage runtime concerns and optimize workspace persistence.

The starter kit includes the following capabilities:

You can deploy and configure the Anthropic Claude Code agent on Red Hat OpenShift AI by using a new agentic starter kit. The kit provides a Containerfile and Kustomize deployment manifests to streamline setup in a secure environment.

The starter kit includes the following capabilities:

You can use the Kale (Kubeflow Automated pipeLines Engine) JupyterLab extension to convert annotated Jupyter notebooks into AI Pipelines without writing Kubeflow Pipelines SDK code. The Kale extension ships pre-installed but disabled by default in the following default data science Jupyter notebook images: Standard Data Science, PyTorch, TensorFlow, TrustyAI, ROCm-PyTorch, and ROCm-TensorFlow.

To enable the extension, run jupyter labextension enable jupyterlab-kubeflow-kale in your workbench terminal and refresh your browser. A Data Science Pipelines Application must be deployed in the same namespace as the workbench. After enabling, a green connection status indicates that KFP is connected; a yellow warning indicates that it is disconnected. Open a Jupyter notebook to activate the Enable toggle, then switch it on to use the Kale metadata editor.

For more information, see Kale documentation.

You can export model catalog metadata to CSV format by using a standalone Python CLI script. The script queries the Model Catalog REST API, paginates through the full result set, and produces an RFC 4180-compliant CSV file that includes all model metadata and custom properties.

The export script requires Python 3.10+ with no additional dependencies and supports options for filtering by source with --source, limiting output count with --limit, and setting authorization headers with --header. The script writes atomically to prevent partial output on failure.

For more information about installation, authentication, and usage, see CSV Exporter for Model Catalog.

You can discover deployed agents and their capabilities through the AgentCard custom resource. When you deploy an agent as a Kubernetes Deployment or StatefulSet with the kagenti.io/type: agent label and a protocol label such as protocol.kagenti.io/a2a, the platform automatically creates an AgentCard that advertises the agent’s capabilities, endpoints, and supported protocols. This enables machine-readable agent-to-agent discovery for multi-agent workflows. For more information, see Kagenti Operator Repository.

You can manage the runtime concerns of deployed agents using the AgentRuntime custom resource. Create an AgentRuntime that references your agent’s Deployment or StatefulSet via spec.targetRef, and the operator automatically injects authentication and identity sidecars into agent pods. This includes an Envoy-based AuthBridge proxy for inbound JWT validation and outbound token exchange, SPIFFE-based workload identity via a spiffe-helper sidecar, and per-agent OpenTelemetry trace configuration. Agents labeled with kagenti.io/type: agent are injected by default, but you can opt out with kagenti.io/inject: disabled. The AgentRuntime also supports per-workload overrides for SPIFFE trust domains, OTEL collector endpoints, and trace sampling rates. For more information, see Kagenti Operator Repository.

You can surface previously-created vector stores as retrieval-augmented generation (RAG) knowledge sources in the Gen AI Studio Playground. Platform engineers define vector stores through ConfigMaps, and AI engineers can select them as knowledge sources when chatting with models in the Playground. This enables rapid RAG experimentation without writing code or re-ingesting data.

This release includes the following capabilities:

Red Hat OpenShift AI provides an MCP (Model Context Protocol) server that enables MCP-compatible clients to interact with your environment through natural-language conversations. When you describe your goals, the MCP server recommends the optimal model from your model registry by matching your intent against benchmarks such as MMLU and HumanEval, with cost comparisons. You can also manage data science projects, create workbenches, and monitor pipeline runs.

When you are ready to deploy, the MCP server generates three production-ready Kubernetes manifests for model serving, auto-scaling, and observability. The MCP server works with AI coding assistants such as Claude Code, OpenCode, and Gemini CLI. For more information, see RHOAI MCP server.

The MCP Catalog provides a centralized experience for discovering, deploying, and experimenting with Model Context Protocol (MCP) servers in Red Hat OpenShift AI. AI Operators and Platform Engineers can browse available MCP servers in a catalog UI, view descriptive metadata about each server’s capabilities and tools, and deploy MCP servers into their namespace directly from the catalog. After deployment, a platform engineer can register deployed MCP servers in the gen AI studio configuration, making them available in the playground for interactive experimentation.

The MCP Catalog ships pre-loaded with MCP servers from Red Hat, technology partners, and the open source community. These servers can be deployed directly from the catalog without sourcing container images or configuring transport manually. Some additional prerequisite steps, such as mirroring images may be required for disconnected deployments or configuring server-specific credentials.

The MCP Catalog relies on the following pre-requisite upstream community components:

+

The Evaluation Stack control plane provides an API REST routing and orchestration layer for AI evaluation, benchmarking, and profiling backends on OpenShift AI. AI engineers can deploy and manage a comprehensive evaluation platform that supports multiple frameworks and execution modes through a unified interface.

The Evaluation Stack control plane includes the following capabilities:

The Kubeflow Spark Operator is available in OpenShift AI as a Developer Preview. This feature provides Apache Spark integration with OpenShift AI, enabling the full lifecycle of Spark applications on Kubernetes. This enables unified orchestration and monitoring of large-scale data processing and preparation Spark jobs alongside ML training and inference workflows.

To enable the Kubeflow Spark Operator, navigate to your dsc.yaml CR and update the kubeflowsparkoperator parameter to the Managed state.

This feature introduces the following capabilities:

You can run evaluations using LM-Eval on OGX with TrustyAI as a Developer Preview feature, using the built-in LM-Eval component and advanced content moderation tools. To use this feature, ensure TrustyAI is enabled, the FMS Orchestrator and detectors are set up, and KServe RawDeployment mode is in use for full compatibility if needed. There is no manual set up required.

Then, in the DataScienceCluster custom resource for the Red Hat OpenShift AI Operator, set the spec.components.ogx.managementState field to Managed.

For more information, see the following resources on GitHub:

LLM Compressor capabilities are available in Red Hat OpenShift AI as a Developer Preview feature. A new workbench image with the llm-compressor library and a corresponding data science pipelines runtime image make it easier to compress and optimize your large language models (LLMs) for efficient deployment with vLLM. For more information, see llm-compressor in GitHub.

You can use LLM Compressor capabilities in two ways:

This feature is available as a Developer Preview.

You can access and consume Model-as-a-Service (MaaS) models directly from the AI Available Assets page in the GenAI Studio.

Administrators can configure a MaaS by enabling the toggle in the Model Deployments page. When a model is marked as a service, it becomes global and visible across all projects in the cluster.

This feature is available as a Developer Preview.

Administrators can add metadata to models during deployment so that they are automatically listed on the AI Available Assets page.

The following table describes the new metadata fields that streamline the process of making models discoverable and consumable by other teams:

This feature is available as a Developer Preview.

OGX remote providers and the SDK are compatible with the Model Context Protocol (MCP) HTTP streaming protocol.

This enhancement enables developers to build fully stateless MCP servers, simplify deployment on standard OGX infrastructure (including serverless environments), and improve scalability. It also prepares for future enhancements such as connection resumption and provides a smooth transition away from Server-Sent Events (SSE).

This feature is available as a Developer Preview.

All Inference Time Scaling (ITS) runtime dependencies are packaged in the Red Hat-maintained Python index, allowing Red Hat AI and OpenShift AI customers to install its_hub and its dependencies directly by using pip.

This enhancement enables users to build custom inference images with ITS algorithms focused on improving model accuracy at inference time without requiring model retraining, such as:

Static hardware profile support is available to help users select training methods, models, and hyperparameters based on VRAM requirements and reference benchmarks. This approach ensures predictable and reliable training workflows without dynamic hardware discovery.

The following components are included:

Human-in-the-Loop (HIL) functionality has been added to the OGX agent to allow users to approve unread tool calls before execution.

This enhancement includes the following capabilities: