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.

What it solves

WrenAI provides a governed semantic layer and AI context layer for AI agents, preventing them from producing "confidently wrong" SQL queries. It ensures that agents understand business meanings—such as approved metric definitions, joins, and units—rather than just database schemas, allowing them to generate trustworthy business intelligence (GenBI) and deploy shareable dashboards.

How it works

It uses the Modeling Definition Language (MDL) to define business logic as reviewable YAML and Markdown files stored in Git. This creates a governed layer between the agent and the data source. The system integrates with existing agents (like Claude Code, Cursor, or LangChain) via a CLI and SDKs, using an Apache DataFusion-based engine to execute queries across 22+ data sources.

Who it’s for

It is designed for agent builders and data teams who want AI agents to produce reliable BI answers and dashboards while keeping business logic version-controlled and open, rather than gated behind a vendor's proprietary UI.

Highlights

  • Agent-Native Integration: Works as a layer for existing agents (Claude Code, Cursor, MCP clients, LangChain) rather than a separate chat UI.
  • Git-Based Governance: Business definitions, metrics, and approved joins are stored as versioned files in Git, allowing for PR reviews and CI/CD workflows.
  • End-to-End GenBI: Enables agents to not only write SQL but also build and deploy browser-side dashboards to platforms like Vercel or Cloudflare Pages.
  • Broad Connectivity: Supports over 22 data sources including BigQuery, Snowflake, PostgreSQL, and ClickHouse via a single engine.

Related

  • Project
    datagallery-ai/dataagent

    An enterprise-grade data agent workbench that turns natural-language questions into verifiable data analysis using semantic grounding and secure, read-only database access.

  • Project
    Lumen-Labs/brainapi2

    BrainAPI is an agent-based system that automatically converts raw text into a structured, queryable knowledge graph, providing traceable and reasoned answers to complex questions.

  • Project
    lightdash/lightdash

    An open-source agentic BI platform that uses a governed context layer to power dashboards, AI agents, and data apps with a software-engineering workflow.

  • Project
    openbkn-ai/bkn-foundry

    BKN Foundry is the backend framework for OpenBKN, an ontology‑driven platform that turns scattered enterprise data and rules into a structured knowledge graph. It provides a Context Loader to fetch only the most relevant facts (cutting token use by ~30 % and boosting accuracy), and a safety layer that validates every agent action against explicit Object‑Action‑Rule‑Constraint definitions, with full audit trails and risk simulation. Users interact via the `openbkn` CLI/SDK (TypeScript/Python) or by adding the `openbkn` skill to LLM agents. Deployed on Kubernetes, it offers unified data access, fine‑grained permissions, and traceable execution for trustworthy AI assistants in business settings.

  • Project
    tencentmusic/supersonic

    SuperSonic is an AI-powered business intelligence platform that combines natural language querying with a semantic data layer to provide reliable, governed data insights.