Wren AI
Text-to-SQL and GenBI on a semantic layer, with an open-source CLI
Overview
Wren AI is a generative BI platform that answers natural-language questions with SQL, charts and dashboards over a semantic layer, connecting to 20+ sources including BigQuery, Snowflake and PostgreSQL, with an embedded API and MCP server. The open-source engine/CLI is Apache-2.0; cloud plans are free, then from $179 a month billed yearly.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 1 Oct 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
- Agentic and Classic modes
- Knowledge base and visualisation
- 2 projects and 2 members
- 10 tables per project
- 80 trial credits for 14 days
- Unlimited dashboards, projects and members
- Embedded AI API
- dbt and external integrations
- Basic RBAC
- Extra credits $0.10 each
- Row- and column-level data control
- MCP and unlimited integrations
- Advanced RBAC and audit logs
- LDAP/AD and OIDC
- Priority support
- Self-hosted, on-prem and air-gapped
- SSO and SCIM 2.0
- Volume discount
What you can produce with Wren AI
- Natural-language questions to SQL, charts and dashboards
- Semantic layer for business context
- 20+ data-source connectors
- Embedded AI API
- MCP server for AI agents
- Open-source context engine and CLI (Apache-2.0)
Wren AI is a thoughtful text-to-SQL product whose semantic layer, governance controls and MCP server make it more credible for real data teams than a bare chat-to-SQL tool. Its open-source story has narrowed: the self-hosted chat app is frozen, and the BI interface is now commercial, with the open repository reduced to a developer CLI. Paid plans are priced for teams rather than individuals. A strong option for organisations wanting governed natural-language analytics; self-hosters should plan around Enterprise Plus or the CLI.
What we found
Wren AI is a generative business-intelligence platform that answers plain-language questions about a company's data by generating SQL, charts and dashboards. It builds a semantic layer describing tables, relationships and business terms so that its AI agent queries data more accurately, and connects to more than 20 sources, including BigQuery, Snowflake, PostgreSQL, ClickHouse, Redshift, Databricks and DuckDB. The hosted product adds dashboards, spreadsheets, a knowledge base, an embedded AI API, dbt integration, Git sync and evaluation tools, and AI agents can call Wren as a sub-agent through its MCP server. In September 2026 it moved its default model to OpenAI's GPT-5.6 Luna.
The open-source side changed in May 2026. The original self-hosted chat app is now Wren GenBI Classic, frozen on a legacy branch without new features or security fixes, and the open repository has become a command-line context engine for developers, licensed under Apache 2.0 rather than AGPL. The graphical BI interface is now commercial only.
Wren AI is made by Canner, Inc., a Delaware company that grew out of the Taiwanese data start-up Canner, started in 2018 and led by Howard Chi. Canner raised a $3.5 million pre-Series A round led by Taiwania Capital in 2022, and the site shows a SOC 2 badge.
The free cloud plan includes 20 credits a month, two projects, two members and ten tables per project, plus 80 trial credits for two weeks. Essential Cloud costs $179 a month billed yearly or $259 monthly, adding unlimited projects, dashboards, the embedded API and basic access controls; Enterprise Cloud, its most popular plan, costs $559 or $799 and adds row- and column-level controls, MCP, audit logs and directory sign-in. Enterprise Plus, for self-hosted and air-gapped use, is licensed by concurrent sessions on annual contracts.
Wren AI suits data teams wanting governed natural-language analytics; self-hosters should note the open app is no longer maintained.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
About this listing
This entry was compiled from publicly available data including Wren AI's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Wren AI unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to Wren AI directly →
Spotted something out of date? Suggest an update →
Related reading
Alternatives to Wren AI
More in Research & Data
