Microsoft ' s Azure Machine Learning documentation on registries describes them as organization-level repositories that sit above individual workspaces. When you publish an asset such as a model, environment, or component to an Azure ML registry, it becomes accessible to any workspace in any subscription within the same Azure tenant, all without physical duplication. The registry maintains a single source of truth with full version history. Option A (Git integration) synchronizes code, not compiled ML artifacts. Option B (pipeline component) packages a reusable pipeline step but does not solve cross-workspace sharing. Option C (shared environment) addresses runtime dependencies, not the full range of ML assets. The registry is the purpose-built solution for centralized governance, version control, and cross-workspace asset sharing — the Microsoft-recommended pattern for mature MLOps organizations.

Microsoft Learn Reference Topic: Share assets across workspaces with Azure Machine Learning registries