#1212th of 51 in RAG, knowledge and searchFor data and documents, data analysis
wrenai
Semantic layer and context engine that lets agents write governed SQL
- Stars
- 18.1k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
14,767 on 21 Apr 202618,143 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
WrenAI is a CLI and Python SDK (pip install wrenai) that gives agents such as Claude Code, Cursor and LangChain a semantic layer written in MDL, plus Git-versioned YAML and Markdown context. Agents generate SQL planned against that layer, validated by dry-plan, and run on an Apache DataFusion engine across 22+ data sources. The earlier Docker chat-style GenBI app is archived on a legacy branch.
Who it is for: Data engineers connecting coding agents to warehouses with governed SQL
Strengths
- Business definitions are YAML and Markdown in Git, reviewable as pull-request diffs
- Dry-plan validation, row limits and structured errors constrain agent-written SQL
- Connects 22+ sources, including BigQuery, Snowflake, PostgreSQL, ClickHouse and DuckDB
- Ships LangChain and Pydantic AI SDKs, an MCP server and agent skills
Weaknesses
- GenBI UI, dashboards, row/column security and user groups are commercial only
- Docker chat BI app moved to legacy/v1 with no new features or security fixes
- Needs an external agent or LLM client; it is not a standalone chat UI
- Detected license is NOASSERTION, though the README states Apache 2.0
What it needs
- Needs Python (pip), A supported data source such as Postgres, BigQuery or Snowflake, An AI agent such as Claude Code or Cursor
- Models: Agent-agnostic: Claude Code, Cursor, Cline, Codex, MCP clients, LangChain
Quick answers
Is wrenai open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Also in RAG, knowledge and search
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | LightRAGGraph-based RAG framework with a REST API server and web UI | 90 out of 100 |
| 3 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 89 out of 100 |
| #4 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 87 out of 100 |