Canner/WrenAI

What is it?

Key features

• 01Generates SQL from natural-language questions using a semantic layer (MDL).
• 02Validates queries with dry-plan checks, row limits and structured error messages.
• 03Deploys agent-built dashboards as browser-side apps to Vercel or Cloudflare Pages.
• 04Stores metric definitions, enums and example queries as version-controlled YAML and Markdown.
• 05Provides a CLI and SDKs for LangChain, LangGraph and Pydantic AI.
• 06Connects to 20+ data sources on an Apache DataFusion engine.

Use cases

• Letting an AI agent answer business questions against a data warehouse with governed SQL.
• Turning an agent-generated analysis into a shareable, filterable dashboard.
• Keeping metric definitions in Git so teams can review changes in pull requests.
• Adding a governed text-to-SQL layer to an existing LangChain or MCP-based agent.

Quick start

1. 1

   Install the CLI from PyPI

   pip install wrenai
2. 2

   Install the agent skill discovery stub

   npx skills add Canner/WrenAI
3. 3

   Open your agent in a project folder and ask it to set up your database with Wren

Things to know

• !License is listed as NOASSERTION in metadata, though the README states the engine is Apache-2.0.
• !Some features such as row- and column-level security, GenBI UI and dashboards are commercial and not in the open-source engine.
• !Setup depends on an AI agent and a database connection, so it is not a standalone point-and-click tool.

Topics

FAQ

What is WrenAI?

Open-source GenBI engine that lets AI agents turn natural-language questions into governed SQL and shareable dashboards over 20+ data sources. WrenAI is a generative BI engine built for AI agents. It sits between an agent and your data warehouse, providing a semantic layer (MDL) that defines metrics, relationships, enums, units and approved joins, so agents generate SQL against business meaning rather than raw schemas alone.

Is WrenAI free to use? What license does it have?

WrenAI is open source under the Other license. Check the license terms before using it in commercial products.

Is WrenAI still maintained?

Actively maintained. The last commit to WrenAI was on Oct 21, 2026.

What can I use WrenAI for?

Letting an AI agent answer business questions against a data warehouse with governed SQL. Turning an agent-generated analysis into a shareable, filterable dashboard. Keeping metric definitions in Git so teams can review changes in pull requests. Adding a governed text-to-SQL layer to an existing LangChain or MCP-based agent.

How do I install WrenAI?

Install the CLI from PyPI: pip install wrenai Install the agent skill discovery stub: npx skills add Canner/WrenAI Open your agent in a project folder and ask it to set up your database with Wren

Where can I get WrenAI?

The source code and installation instructions are on GitHub: https://github.com/Canner/WrenAI