
Wren AI
β Text source-checked Nov 13, 2026Source-checked against the vendor's site Β· rebuilt from the vendor's own pagesProfile updated Link checked Pricing captured How we rate
In short
Wren AI is an open-source semantic layer and text-to-SQL engine supporting 22+ data sources. It offers free self-hosting or paid cloud tiers for enterprise governance and multi-model AI integration.
The vendor says that the product uses a Modeling Definition Language (MDL) semantic layer paired with an AI context layer and a governed execution engine running across 22+ data sources.
The core engine, including the MDL semantic layer, text-to-SQL pipeline, MCP server, CLI, and connectors, is licensed under Apache-2.0 and is free and self-hostable. Wren AI integrates with over 50 agent frameworks, including Claude Code, Cursor, Cline, and Codex.
The open-source edition is intended for individual developers using the CLI and MCP server without a user interface.
According to Wren AI: The core engine, Including the MDL semantic layer, text-to-SQL pipeline, MCP server, CLI, and connectors, is licensed under Apache-2.0 and is free and self-hostable. Its pages list this strength: The core engine is Apache-2.0 licensed, free, and self-hostable.
β The AI Tool Bible editorial team
Pros
- β The core engine is Apache-2.0 licensed, free, and self-hostable.
- β Wren AI works with over 50 agent frameworks.
- β The vendor says that the product supports 22+ data sources on a single Apache DataFusion engine.
Pricing (captured )
| Tier | Monthly | Annual | Key features |
|---|---|---|---|
| Essential Cloud | β | $179 /month, billed annually |
|
| Enterprise Cloud | β | $559 /month, billed annually |
|
| Enterprise Plus | β | Contact Us |
|
Prices change; we show the grid as captured on Nov 7, 2026. Check current pricing on the vendor's site β
Facts
- Platforms
- api (not source-checked)
- API available
- Yes (not source-checked)
- Free trial
- Yes
- Open source
- Yes (license: NOASSERTION)
- GitHub stars
- 18,150 (checked Nov 13, 2026) (not source-checked)
- Last GitHub push
- Nov 13, 2026 (not source-checked)
- First commit
- Mar 2024 (not source-checked)
- Model used
- Multi-model (OpenAI, Anthropic, Gemini, self-hosted) (not source-checked)
- Vendor pages
- Changelog
- Package downloads (30 d)
- 20,831 Β· pypi wrenai Β· checked Oct 23, 2026 (not source-checked)
- Hacker News
- 2 stories Β· top 2 points Β· last Jul 26, 2026 Β· checked Oct 23, 2026
- Earliest Wayback capture
- 2024-03-20 (earliest archived capture of the site, not a launch date)
Where this tool sits
Use cases
Recent updates from Wren AI
Frequently asked
- How much does Wren AI cost?
- The open-source edition is free and self-hostable. Cloud options include Essential at $179/month and Enterprise at $559/month, both billed annually. The core engine and MDL semantic layer are licensed under Apache-2.0.
- Which AI models does Wren AI support?
- Wren AI uses a multi-model approach, supporting OpenAI, Anthropic, Gemini, and self-hosted models. It integrates with over 50 agent frameworks, including Claude Code, Cursor, Cline, and Codex, via its MCP server and CLI.
- Is Wren AI suitable for individual developers?
- Yes, the open-source edition is intended for individual developers. It provides the CLI and MCP server without a user interface, allowing free self-hosting of the core engine, text-to-SQL pipeline, and connectors.
- What data sources can Wren AI connect to?
- The governed execution engine runs across 22+ data sources. It features a Modeling Definition Language (MDL) semantic layer and an AI context layer to facilitate natural language analytics and data governance.
- What are the main use cases for Wren AI?
- Primary use cases include text-to-SQL, semantic-layer implementation, agentic business intelligence, data governance, and natural-language analytics. It helps users query data using natural language through its AI context layer.