Data and databases · Independent · 20 Oct 2026

Canner/WrenAI

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

← Data and databases
WrenAI: text-to-SQL engine. Turns plain English into database queries and dashboards.

In simple English

This tool helps AI assistants write correct database queries and build web pages from your raw data. Instead of letting an AI guess how your database is structured, you give it clear rules written in plain files. It connects to popular databases like PostgreSQL and Snowflake. You manage your data rules using normal Git commands. It works directly inside coding tools you might already use, such as Claude Code or Cursor.

What it is

WrenAI is an open-source tool that turns natural language into governed SQL queries and dashboards by combining a semantic layer with an AI context layer. It bridges the gap between raw data sources and AI coding agents to ensure generated answers are reliable.

What it is good for

Solo builders and small teams who want to ask questions about their data using AI without getting incorrect SQL or broken queries. It removes the need to build a custom dashboard from scratch every time you want to inspect business metrics.

Stars18k
LicenceCustom
Latestwren-pydantic-v0.3.1 (2026-10-20)checked 20 Oct 2026
Last code change2026-10-20
Written inPython
Setup effort
3 / 5
Payoff
4 / 5
Good
  • Works directly inside existing AI coding assistants and command-line workflows.
  • Keeps all your business definitions and database rules in version-controlled files.
  • Supports over twenty popular database sources including PostgreSQL and Snowflake.
Watch for
  • Requires comfort with command-line tools and Python package installation.
  • Advanced enterprise features and multi-user access control require a paid commercial plan.
  • Complex data schemas need manual guidance in text files before the AI understands them well.
Replaces

Writing raw SQL queries by hand or building custom internal dashboards for every database question.

Works well with

Cursor or Claude Code for running the AI commands against your project folders.

Similar repositories
  • cube-js/cube21k stars

    A headless semantic layer that organizes data definitions for applications and APIs without the AI agent focus.

Also reviewed on Repo Radar
  • meilisearch/meilisearch59k stars

    A search engine you run yourself, built for fast answers and forgiving spelling.

  • beekeeper-studio/beekeeper-studio24k stars

    A desktop window onto a database, so you can read and edit rows without writing commands.

  • sqliteai/sqlite-vector1.1k stars

    An add-on that gives the single-file SQLite database meaning-based search, with its own accuracy figures printed in the README.

Install
pip install wrenai
npx skills add Canner/WrenAI

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Data & Research › Analytics & Business Intelligence › Business Intelligence.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.