Data Formulator - AI Data Tools Tool

Overview

Data Formulator is an open-source project from Microsoft that uses AI to simplify data transformation and visualization. It connects to common data sources — including MySQL, PostgreSQL, Azure services, and Amazon S3 — and gives analysts and engineers an interactive, visual surface to explore datasets, specify charts by dragging and dropping, and iterate on results rapidly. The tool pairs that visual interface with AI-driven agents that generate SQL queries and transformation logic, letting users obtain parameterized queries, preview transformed results, and refine visualizations without writing SQL from scratch. Designed to accelerate exploratory analysis and dashboard prototyping, Data Formulator targets data analysts, BI engineers, and developer teams who want faster turnarounds from data to insight. As an MIT-licensed project maintained on GitHub, it’s intended to be integrated into existing workflows or deployed alongside cloud data platforms. According to the project repository, Data Formulator provides interactive chart building, automated query generation, and connectors for cloud and relational stores, helping teams move from raw data to shareable visualizations with fewer manual steps.

GitHub Statistics

• Stars: 14,693
• Forks: 1,334
• Contributors: 24
• License: MIT
• Primary Language: TypeScript
• Last Updated: 2025-12-09T01:42:54Z
• Latest Release: 0.5.1

According to the GitHub repository, Data Formulator is actively maintained and has strong community interest: 14,693 stars, 1,334 forks, and 24 contributors. The project is released under the MIT license and shows recent commits (last recorded commit: 2025-12-09), indicating ongoing development and updates. Those metrics suggest healthy adoption and contributor activity for an open-source data tool from a major vendor.

Installation

Install via docker:

git clone https://github.com/microsoft/data-formulator.git

cd data-formulator

docker compose up --build

Key Features

• Connectors for MySQL, PostgreSQL, Azure storage/services, and Amazon S3 data sources
• Interactive drag-and-drop chart builder for specifying visualization types and encodings
• AI agents that generate SQL queries and transformation logic from user intent
• Preview transformed datasets and results before committing queries or visualizations
• Exportable query artifacts (generated SQL) to integrate with BI pipelines or apps

Community

Community engagement is strong: the repository has 14,693 stars, 1,334 forks, and 24 contributors, and is MIT licensed. Active commits (most recent recorded: 2025-12-09) and public GitHub issues/discussions provide the primary channels for feedback, bug reports, and contributions.

Key Information

• Category: Data Tools
• Type: AI Data Tools Tool