Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake…
Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ functions, Session for…
The enforcement arm of the handbook rules (handbook/meta/handbook/): the checks that keep the documentation system whole. Run it when a change touches documentation — handbook pages, free-floating .md files, script headers, generated indexes — and periodically as a scheduled sweep.
Maintain and extend the dockndevai MCP server suite (mcp-keycloak, mcp-kubernetes, mcp-oci, mcp-kafka, mcp-clickhouse, mcp-debezium, mcp-azure, mcp-azure-devops, mcp-percona-pg). Use when adding or changing a tool, touching the security/policy layer, bumping dependencies, cutting a release, or publishing to npm or an…