microsoft/data-formulator

🪄 Data Formulator is an interactive AI-powered data analysis system makes it easy to connect, explore and visualize data.

Data & analyticsPython

1.9 Steady Magnitude out of 10. Star growth looks organic. Data as of September 18, 2026.

Open on Seismograph Open on GitHub

About the project

An interactive data analysis system from Microsoft Research: AI agents connect to files, databases and BI tools while users explore data and build charts via UI and natural language.

Useful for

Connect a CSV or database and build charts through a dialogue with the agent
Branch the analysis into multiple questions in a Data Thread and compare results
Run locally via uvx or Docker and extract data from a screenshot or text

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

6 stars so far today, about 8 expected by the end of the day.
Over the last two days the pace is 1.5× that of the previous week and a half.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 17,261
Stars in a day: 8
Forks: 1,680
Issues and pull requests: 440
Watchers: 114
Language: Python
License: MIT
Latest release: 0.8b1 · August 15, 2026
Created: June 7, 2024
Last push: September 18, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 15, 2026GitHub Trending this month: #17, +1,158 stars
September 14, 2026GitHub Trending this month: #17, +1,141 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/microsoft/data-formulator.svg?lang=en)](https://gitnova.dev/en/r/microsoft/data-formulator)

Similar projects

5.2
realZachi/pg-jev
A PostgreSQL extension that lets you filter, rank and classify table rows using plain-language conditions via TypeSafe's Jev model.

Early signalData & analyticsShell+96 stars in a day
4.7
bilawalsidhu/gods-eye-view
A browser-based spy-satellite simulator on a photorealistic 3D globe that unifies public feeds: aircraft, ships, satellites, earthquakes, cameras, and traffic. Runs locally, with each layer as a separate module.

CoolingData & analyticsJavaScript+517 stars in a day
4.4
liyupi/ai-model-world
A Next.js static site that turns 556 large language models into pixel characters in a vendor town, with leaderboards, a release timeline and search by model, vendor or capability. Data comes from Epoch AI, models.dev,…

Early signalData & analyticsTypeScript+31 stars in a day
4.4
roboflow/supervision
Python library of reusable computer vision utilities: dataset loading and conversion, frame annotation, tracking and zone analysis on top of any detection or segmentation model.

BreakoutData & analyticsPython+68 stars in a day
4.1
D4Vinci/Scrapling
An adaptive Python web scraping framework: the parser relocates elements when site markup changes, fetchers bypass anti-bot systems like Cloudflare Turnstile, and the spider system scales to concurrent multi-session…

SteadyData & analyticsPython+233 stars in a day
3.7
koala73/worldmonitor
Real-time situational awareness dashboard: aggregates news with AI summarization, tracks geopolitics, infrastructure, finance, and flight data on a world map.

SteadyData & analyticsTypeScript+140 stars in a day