# microsoft/data-formulator

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

Repository: https://github.com/microsoft/data-formulator
Canonical: https://ross.abutalabs.com/products/data-formulator
Homepage: https://data-formulator.ai/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-24T14:19:43+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 86, longevity 58
- inputs: {"age_days": 817, "days_push": 9, "days_rel": 18, "gap_med": 33, "n_releases_24m": 14}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 17011, forks 1655 (observed 2026-08-28T04:11:17.569595+00:00)

## What it is
Data Formulator is an AI-powered interactive data analysis and visualization application from Microsoft that lets users connect data sources and explore them through AI agents and visualizations. It provides data connectors and a 'Data Threads' workspace for branching exploratory analysis.

## Use cases
- visualize csv data with ai
- explore datasets without writing code
- connect llm agents to databases and files
- create charts from natural language questions
- branch exploratory data analysis threads
- build ai-assisted data dashboards

## When to choose
- you want AI-assisted exploratory data analysis and charting
- you need to connect multiple data sources for LLM-driven analysis
- you prefer a visual, no-code data exploration workspace

## When to avoid
- you need production BI reporting at enterprise scale
- you want fully deterministic, code-based visualization pipelines
- you cannot send data to LLM providers

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, machine-learning, llm-inference, agent-framework, charts, analytics
- domain: data-visualization, data-science, artificial-intelligence, analytics, large-language-models
- platform: python, cross-platform, self-hosted
- tags: ai-powered, data-exploration, no-code, data-connectors, visualization-agents, research-prototype, web-server

## Member repositories
- microsoft/data-formulator (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:17.569595+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:03:40.547032+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/data-formulator (fetched 2026-08-28T04:11:17.569595+00:00, sha 883395b82f98)
  - homepage: https://data-formulator.ai/ (fetched 2026-08-29T08:01:43.841339+00:00, sha d231dfd91ec6)
  - registry_pypi: https://pypi.org/pypi/data-formulator/json (fetched 2026-08-29T08:01:43.843804+00:00, sha bbdacc07e090)
- Data as of 2026-08-30T08:39:29.467469+00:00.