data-formulator vs WrenAI
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. — versus — 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).
Both 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.
| data-formulator | WrenAI | |
|---|---|---|
| Stars | 17k | 17k |
| Forks | 1.6k | 2.0k |
| Language | Python | Python |
| License | MIT | NOASSERTION |
| Last activity | 2 days ago | 4 days ago |
| Topics | agents | agents |
| Curated connections | 3 | 3 |
data-formulator — the 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.
WrenAI — the curator's take
The strongest open answer to 'my agent writes confidently wrong SQL': business definitions, approved joins and past queries live in reviewable files, not prompts, and dry-plan validation catches errors before execution. Agent-driven by design (skills + CLI, works through Claude Code/Cursor). Skip for one-off charts from a CSV — the context layer is the point, and it takes real setup.