dbt-core-mcp: dbt-core-mcp is a Model Context Protocol server that enables AI assistants to interact with dbt projects without requiring any dbt dependencies. It respects the user's Python environment, automatically detects dbt version and adapters, and provides tools for querying metadata, executing SQL, running models, testing, and lineage analysis. It supports natural language control and smart selection based on changes.; learn-claude-code: This repository provides a hands-on tutorial to learn how modern AI agents work by building one from scratch, emphasizing the core loop of model-tool interaction. It distills complex agent concepts into simple, iterative versions, from basic Bash agents to sophisticated skill-based systems.
Explore your project: List all models, sources, tests.
Learning to build modern AI coding agents from scratch