metaxy

npx skills add majiayu000/claude-skill-registry --skill metaxy --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Metaxy Metaxy is a metadata layer for multi-modal Data and ML pipelines that manages and tracks feature versions, dependencies, and data lineage across complex computational graphs. ## Core Concepts ### Feature Definitions To define a feature, create a class inheriting from `mx.BaseFeature` with a `FeatureSpec` metaclass argument: ```python import metaxy as mx class MyFeature( mx.BaseFeature, spec=mx.FeatureSpec( key="my/feature", id_columns=["sample_id"], fields=["embedding", "score"], ), ): sample_id: str embedding: list[float] score: float ``` To add dependencies between features, use the `deps` parameter with `FeatureDep`. To specify field-level dependencies (for partial data dependencies processing), use `FieldSpec` with `FieldDep` or `FieldsMapping`. ### Data Versioning Metaxy automatically tracks sample versions and propagates changes through the dependency graph. To trigger recomputation when code changes, set `code_version` on `FieldSpec`: ```python fields = [ mx.FieldSpec(key="embedding", code_version="2"), # Bump to invalidate downstream ] ``` ### Metadata Stores To configure a metadata store, create a `metaxy.toml` file or use programmatic configuration: ```python wit

mx graph render            # Terminal visualization
mx graph push --store dev  # Push graph to store
mx list features --verbose     # List features with dependencies
mx graph render                # Visualize feature graph
mx metadata status --all-features  # Check metadata freshness (expensive!)
mx migrations apply            # Apply pending migrations
mx mcp                         # Start MCP server for AI assistants