WrenAI
An open-source generative BI engine that gives AI coding agents a governed semantic layer, so natural-language questions become correct SQL and shareable dashboards across more than 20 data sources.
WrenAI is an open-source generative BI (GenBI) engine that gives AI agents such as Claude Code, Cursor and LangChain a governed semantic layer and context layer for working with a business's data. Rather than only exposing a schema, it captures approved metric definitions, enums, units, joins and worked examples as reviewable YAML and Markdown files stored in a repository the user owns.
With this context, an agent turns natural-language business questions into governed SQL, executes it against a connected data source, and can turn the result into a shareable, filterable dashboard, working across more than 20 data sources including BigQuery, Snowflake, PostgreSQL, ClickHouse, Redshift and Databricks.
It installs as a Python CLI with connector-specific extras, and an agent skill package teaches a coding agent the workflow so it can set up a connection, enrich the project with business context, and generate SQL and dashboards from a prompt.