data-formulator

Microsoft's AI data-visualization workbench: connect files, DBs or Databricks, ask in plain language, and agents write the transforms behind 30+ chart types you branch and restyle.

16,845 1,630 Python MITupdated yesterday

agents

View on GitHubDispute this mapping →

Curator's take

Reach for it when you have tabular data and want charts without hand-writing pandas or Vega: the agent authors the transform, you steer with UI encodings instead of prompt-only chat, and the Data Thread keeps every branch reproducible. Runs locally via `uvx` on your own key, with loaders for Postgres, MySQL, ClickHouse, BigQuery, Kusto, S3/Athena, Mongo and Databricks, and DuckDB doing the local crunching. Not a BI platform — no semantic layer, governed metrics, permissions or scheduled dashboards — so don't hand it to a business team as their reporting stack. Microsoft still calls it a research prototype: 0.8 is beta, it's single-user, and wide tables burn tokens fast.

Mapped by ShipWithAI editors · links verified

README.md

Data Formulator: AI-powered Data Visualization

🪄 Explore data with visualizations, powered by AI agents.

Why Data Formulator?

Working with data is hard for two simple reasons:

Data lives everywhere. Connecting agents to files, databases, warehouses, and BI tools takes time. It is even harder when agents start answering before the relationships between data sources are clear.
Questions evolve as you explore. Each answer can lead to follow-up questions, comparisons, and new directions. A long chat history makes it hard to see where you are and how you got there.

Data Formulator provides one visual workspace for exploring and analyzing data:

Data connectors give agents a common way to connect to different data sources and maintains a data memory to remember the relationships between them.
Data Threads let you branch into different questions, compare paths, and use visualizations to discover deeper insights without losing context.

https://github.com/user-attachments/assets/8e4f8a08-6423-4227-a1f7-559e0126ce31

[!TIP] Love the charts? They're built on Flint. It's an open-source visualization language that compiles compact chart specs into polished visualizations.

News 🔥🔥🔥

[08-15-2026] Data Formulator 0.8 beta 1 (0.8.0b1) introduces:

One unified flow: load data, ask questions, review results, and branch in the Data Thread.
More data sources: use files, local folders, databases, and platforms such as Databricks.
Better charts: explore more Flint-powered charts, recommendations, themes, and styling tools.

Preview with pip install --pre data_formulator==0.8.0b1 or uvx data_formulator@0.8.0b1. Install the latest stable release (0.7) with pip install data_formulator or run instantly with uvx data_formulator.

See the changelog for release details.

Previous Updates

Here are milestones that lead to the current design:

v0.7 (05-28-2026): Turn ANY data into insights in five steps — connect governed data sources, load via agents, explore with the unified DataAgent + Data Thread, refine 30+ chart types (semantic chart engine powered by Flint) with a style-refinement agent, and share as reports. Plus persistent sessions & workspaces and a multilingual (English/Chinese) UI

Continue your stack

What teams reach for next — and why each earns a place beside data-formulator. Ranked by curator confidence.

Pairs well with

ktx

Self-improving context layer for data agents — ingests dbt/Looker/wikis, maps your warehouse, builds a semantic layer with approved metrics, and serves Claude Code/Codex via CLI and MCP.

Why it fitsktx curates the warehouse semantics and approved metrics that a data question should resolve against; Data Formulator is the exploration and charting surface on top. Pair them when 'revenue' has to mean one thing across a team.

Alternative to See all + compare →

WrenAI

Open-source GenBI engine: agents write governed SQL and deploy shareable dashboards over 22+ data sources, grounded in a Git-friendly context layer (MDL semantics, definitions, memory).

Why it fitsBoth turn plain questions into charts over your own data, but Wren governs a shared semantic layer and publishes team dashboards, while Data Formulator is a single-user exploration surface where you branch and restyle visualizations by hand.

Built with / on

litellm

Open-source AI gateway: call 100+ LLM providers in OpenAI format via a Python SDK or self-hosted proxy — with cost tracking, virtual keys, guardrails, load balancing and logging.

Why it fitsLiteLLM is a hard dependency, so one install talks to OpenAI, Anthropic, Gemini, Ollama or any of LiteLLM's 100+ providers on your own key — swap models without touching the app.