astronomer/agents

AI agent tooling for data engineering workflows.

What it solves

This project provides a suite of AI agent tooling designed to streamline data engineering workflows, specifically for those working with Apache Airflow and various data warehouses. It bridges the gap between AI coding agents and the complex operational tasks of managing data pipelines, querying warehouses, and developing DAGs (Directed Acyclic Graphs).

How it works

The project implements two primary mechanisms to extend AI agents:

  1. MCP Server: An Model Context Protocol (MCP) server that provides full Airflow REST API integration, allowing agents to manage DAGs, trigger runs, and check system health.
  2. Skills: Specialized capabilities that can be added to AI coding agents (like Claude Code or Cursor). These skills include:
    • Data Discovery: Tools for schema discovery and SQL-based analysis using a background Jupyter kernel.
    • Lineage: Tools to trace upstream and downstream data dependencies.
    • DAG Development: Tools for authoring, testing, debugging, and deploying Airflow DAGs.
    • Integrations: Specialized support for dbt Core and dbt Fusion via Astronomer Cosmos.

Who it’s for

Data engineers and practitioners who use Apache Airflow (either open-source or via Astronomer's managed platform) and need to integrate AI assistance into their development environment to automate pipeline management and data analysis.

Highlights

  • Broad Compatibility: Works with 25+ AI coding agents including Claude Code, Cursor, and VS Code.
  • Extensive Warehouse Support: Connects to Snowflake, BigQuery, PostgreSQL, and 25+ other databases via SQLAlchemy.
  • Airflow Integration: Full REST API access for DAG management and failure diagnosis.
  • Developer Tooling: Includes a dedicated CLI tool (af) for direct terminal interaction with Airflow.

Related

  • Project
    aws/agent-toolkit-for-aws

    A toolkit that provides AI coding agents with the tools, knowledge, and guardrails needed to build, deploy, and manage applications on AWS.

  • Project
    dbt-labs/dbt-agent-skills

    A collection of Agent Skills that enable AI agents to understand and execute dbt workflows, including analytics engineering, semantic layer management, and project migrations.

  • Project
    awslabs/agent-plugins

    A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.

  • Project
    addyosmani/agent-skills

    A library of production-grade engineering skills and workflows for AI coding agents to ensure they follow senior-level best practices in software development.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.