databricks-solutions / ai-dev-kit

Databricks AI Dev Kit --- Overview AI-Driven Development (vibe coding) on Databricks just got a whole lot better. The **AI Dev Kit** gives your AI coding assistant (Claude Code, Cursor, Windsurf, etc.) the trusted sources it needs to build faster and smarter on Databricks. --- What Can I Build? • **Spark Declarative Pipelines** (streaming tables, CDC, SCD Type 2, Auto Loader) • **Databricks Jobs** (scheduled workflows, multi-task DAGs) • **AI/BI Dashboards** (visualizations, KPIs, analytics) • **Unity Catalog** (tables, volumes, governance) • **Genie Spaces** (natural language data exploration) • **Knowledge Assistants** (RAG-based document Q&A) • **MLflow Experiments** (evaluation, scoring, traces) • **Model Serving** (deploy ML models and AI agents to endpoints) • **Databricks Apps** (full-stack web applications with foundation model integration) • ...and more --- Choose Your Own Adventure | Adventure | Best For | Start Here | |----------------------------------|----------|------------| | :star: **Install AI Dev Kit** | **Start here!** Follow quick install instructions to add to your existing project folder | Quick Start (install) | **Visual Builder App** | Web-based UI for Databricks development | | | **Core Library** | Building custom integrations (LangChain, OpenAI, etc.) | | | **Skills Only** | Provide Databricks patterns and best practices (without MCP functions) | Install skills | | **MCP Tools Only** | Just executable actions (no guidance) | Register MCP server | --- Quick Start Prerequisites • uv - Python package manager • Databricks CLI - Command line interface for Databricks • AI coding environment (one or more): • Claude Code • Cursor • Gemini CLI Install in existing project By default this will install at a project level rather than a user level. This is often a good fit, but requires you to run your client from the exact directory that was used for the install. _Note: Project configuration files can be re-used in other projects. You find these configs under .claude, .cursor, or .gemini_ Mac / Linux **Basic installation** (uses DEFAULT profile, project scope) Advanced Options (click to expand) **Global installation with force reinstall** **Specify profile and force reinstall** **Install for specific tools only** **Next steps:** Respond to interactive prompts and follow the on-screen instructions. • Note: Cursor and Copilot require updating settings manually after install. Windows (PowerShell) **Basic installation** (uses DEFAULT profile, project scope) Advanced Options (click to expand) **Download script first** **Global installation with force reinstall** **Specify profile and force reinstall** **Install for specific tools only** **Next steps:** Respond to interactive prompts and follow the on-screen instructions. • Note: Cursor and Copilot require updating settings manually after install. Visual Builder App Full-stack web application with chat UI for Databricks development: Core Library Use directly in your Python projects: Works with LangChain, OpenAI Agents SDK, or any Python framework. See databricks-tools-core/ for details. --- What's Included | Component | Description | |-----------|-------------| | | Python library with high-level Databricks functions | | | MCP server exposing 50+ tools for AI assistants | | | 20 markdown skills teaching Databricks patterns | | | Full-stack web app with Claude Code integration | --- Star History --- License (c) 2026 Databricks, Inc. All rights reserved. The source in this project is provided subject to the Databricks License. See LICENSE.md for details. Third-Party Licenses | Package | Version | License | Project URL | |---------|---------|---------|-------------| | fastmcp | ≥0.1.0 | MIT | https://github.com/jlowin/fastmcp | | mcp | ≥1.0.0 | MIT | https://github.com/modelcontextprotocol/python-sdk | | sqlglot | ≥20.0.0 | MIT | https://github.com/tobymao/sqlglot | | sqlfluff | ≥3.0.0 | MIT | https://github.com/sqlfluff/sqlfluff | | litellm | ≥1.0.0 | MIT | https://github.com/BerriAI/litellm | | pymupdf | ≥1.24.0 | AGPL-3.0 | https://github.com/pymupdf/PyMuPDF | | claude-agent-sdk | ≥0.1.19 | MIT | https://github.com/anthropics/claude-code | | fastapi | ≥0.115.8 | MIT | https://github.com/fastapi/fastapi | | uvicorn | ≥0.34.0 | BSD-3-Clause | https://github.com/encode/uvicorn | | httpx | ≥0.28.0 | BSD-3-Clause | https://github.com/encode/httpx | | sqlalchemy | ≥2.0.41 | MIT | https://github.com/sqlalchemy/sqlalchemy | | alembic | ≥1.16.1 | MIT | https://github.com/sqlalchemy/alembic | | asyncpg | ≥0.30.0 | Apache-2.0 | https://github.com/MagicStack/asyncpg | | greenlet | ≥3.0.0 | MIT | https://github.com/python-greenlet/greenlet | | psycopg2-binary | ≥2.9.11 | LGPL-3.0 | https://github.com/psycopg/psycopg2 | --- Acknowledgments MCP Databricks Command Execution API from databricks-exec-code by Natyra Bajraktari and Henryk Borzymowski.