model-registry

Manage machine learning models in the OpenShift AI Model Registry.

48|31|Updated Feb 2, 2026

Search Tags:#versioning #machine learning #model management #model registry #open shift

Ready to run

npx skills add https://github.com/RHEcosystemAppEng/agentic-plugins --skill model-registry-rhecosystemappeng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-registry
Source: https://github.com/RHEcosystemAppEng/agentic-plugins/tree/main/rh-ai-engineer/skills/model-registry
Command: npx skills add https://github.com/RHEcosystemAppEng/agentic-plugins --skill model-registry-rhecosystemappeng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openshift, rhoai, resources_create_or_update, resources_get, resources_list, list_registered_models, get_registered_model, list_model_versions, get_model_version, get_model_artifacts, get_model_benchmarks, get_catalog_model_artifacts, list_data_science_projects, list_data_connections, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the complexities of managing machine learning models in the OpenShift AI Model Registry, simplifying model registration, versioning, and cross-environment promotion.

Core Features & Use Cases

Model Registration: Register new models in the registry.
Versioning: Create and manage versions of models.
Model Management: List, view, and manage model details and artifacts.
Environment Promotion: Promote models across development, staging, and production environments.
Use Case: Ideal for OpenShift administrators and AI/ML engineers looking to streamline their machine learning model lifecycle.

Quick Start

Frequently Asked Questions about model-registry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage machine learning model versioning in OpenShift AI?▼

You can manage model versioning in OpenShift AI by using the Model Registry to register models, create new versions, and retrieve version-specific artifacts and benchmarks. This streamlines tracking iterations and updates throughout the machine learning lifecycle.

What is the process for promoting ML models across development, staging, and production environments?▼

Promoting ML models across environments requires moving registered model versions through development, staging, and production stages using the OpenShift AI Model Registry. This ensures controlled deployment and lifecycle management of your machine learning artifacts.

Do I need an OpenShift MCP server to handle model registration and artifacts?▼

Yes, handling model registration and managing artifacts requires the OpenShift MCP server and its associated tools. These dependencies are necessary to perform operations for listing, viewing, and managing machine learning models in the registry.

How do I list registered models and retrieve their artifacts in OpenShift AI?▼

To list registered models and retrieve artifacts in OpenShift AI, you use the Model Registry tools to query existing models and fetch associated artifacts. This allows administrators and AI engineers to view model details and benchmark data.

Can I retrieve model benchmarks and data science projects using the OpenShift AI Model Registry?▼

Yes, you can retrieve model benchmarks and list data science projects using the OpenShift AI Model Registry. The registry integrates with data connections to provide comprehensive management of model artifacts and performance metrics.