databricks-solutions/ai-dev-kit

Databricks Toolkit for Coding Agents provided by Field Engineering

What it solves

Databricks AI Dev Kit provides a set of tools and patterns to bring Databricks expertise into the AI coding environments developers already use. It bridges the gap between general-purpose AI assistants (like Cursor, Claude Code, and GitHub Copilot) and the specific configurations, APIs, and best practices required to build on the Databricks platform.

How it works

The kit is composed of four main components that can be used independently or together:

  • Skills: Curated patterns and best practices that teach AI assistants how to handle Databricks-specific tasks. These are installed via the Databricks CLI (databricks aitools install) and integrated into the editor's configuration.
  • MCP Server: A Model Context Protocol (MCP) server that exposes over 40 Databricks tools as actionable functions for AI clients.
  • Visual Builder App: A full-stack web application with a chat UI designed specifically for Databricks development.
  • Core Library (databricks-tools-core): A Python library providing high-level functions for interacting with Databricks, compatible with frameworks like LangChain and OpenAI Agents SDK.

Who it’s for

Developers and data engineers who build on Databricks and prefer using their own local IDEs or AI-powered editors (such as Cursor, Claude Code, Gemini CLI, or Windsurf) rather than the native Databricks workspace.

Highlights

  • Broad Editor Support: Compatible with a wide range of AI coding tools including Claude Code, Cursor, GitHub Copilot, and Gemini CLI.
  • Extensive Toolset: Provides capabilities to build Spark Declarative Pipelines, Unity Catalog governance, MLflow experiments, and Model Serving endpoints.
  • Flexible Deployment: Offers both a project-level and global installation for skills and tools.
  • Genie Code Integration: Includes a specific path for uploading skills directly into Databricks workspaces for use with Genie Code.

Related

  • Project
    microsoft/skills-for-fabric

    A collection of reusable AI assistant instructions and MCP servers that help AI coding tools understand and operate Microsoft Fabric workloads, APIs, and best practices.

  • 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
    giuseppe-trisciuoglio/developer-kit

    A modular AI plugin system for Claude Code and other AI CLIs that provides domain-specific agents, skills, and rules to improve the quality of AI-generated code across various frameworks.

  • Project
    codeaholicguy/ai-devkit

    AI DevKit is a local npm‑based control plane that unifies configuration, monitoring, cross‑agent messaging, searchable SQLite memory, and composable engineering “skills” (requirements, design, testing, review, etc.) for many AI coding assistants such as Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot. It lets teams manage multiple agents from a single console, keep project conventions in a searchable store, and enforce a senior‑engineer workflow without modifying the underlying LLMs.

  • Project
    Aaronontheweb/dotnet-skills

    A library of 30 skills and 5 specialized agents for AI coding assistants to ensure .NET development follows production-tested patterns and best practices.