WrenAI: An open-source generative BI engine that gives AI agents a governed semantic layer and AI context layer for turning business questions into SQL and dashboards.
What problem it solves
AI agents often produce plausible SQL without the business definitions, approved joins, units, and examples needed to make results trustworthy. Teams also need a reviewable way to manage that context and turn governed answers into shareable dashboards across existing data sources.
Key features
Governed semantic and context layers — Business meaning is represented through the Modeling Definition Language, including models, relationships, metrics, enums, units, joins, and worked examples. Context is stored as reviewable YAML and Markdown in a repository the team owns.
Source: README, core
Agent-driven SQL and dashboards — Agents can turn natural-language questions into governed SQL, execute queries, and build browser-side dashboards that can be filtered and shared. The workflow supports both answers and deployed GenBI applications rather than SQL alone.
Source: README, skills
Governed execution safeguards — Queries are planned against semantic definitions and checked through execution primitives that include dry-plan validation, row limits, value profiling, and structured errors. These mechanisms help keep agent-generated SQL within defined guardrails.
Source: README, core
Works with existing agents and data stacks — The engine is designed to operate through agents such as Claude Code, Cursor, Cline, Codex, MCP clients, and LangChain. It supports existing warehouses, transformation pipelines, semantic models, and 22+ data sources on one engine.
Source: README
Reviewable deployment workflow — Project context is kept in YAML and Markdown, while Git Sync can promote a repository into a governed team deployment. Metric changes can be reviewed as diffs and managed through normal software workflows.
Source: README, docs
Quick start
Copied verbatim from the project's README.
pip install wrenainpx skills add Canner/WrenAIWho it may suit
Inference: This project may suit teams building agent-driven business intelligence workflows that need governed SQL, reviewable business context, and dashboard generation across existing data sources.
Topics to discuss
Which additional agent frameworks and SDK integrations should be prioritized for native support?
Which context formats and review workflows would make business definitions easiest to maintain in Git?
Which connectors or data sources are most important to add or improve next?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/Canner/WrenAI#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…