WrenAI

Report Abuse

Basic Information

Wren AI is an open-source GenBI agent designed to let users query databases in natural language and get accurate SQL, charts, and AI-generated insights. The repository provides the components needed to connect to common data sources, run a semantic layer that encodes schema and metrics, and integrate with large language models to generate text-to-SQL and text-to-chart outputs. It supports both self-hosted OSS installation and a managed cloud option and includes documentation, configuration examples, and architectural diagrams. The project targets analysts, developers, and product teams who want to add conversational data access, automated reporting, or embedded query capabilities to applications while keeping LLM outputs governed by a semantic model.

Links

Categorization

App Details

Features
The project offers natural language querying that produces precise SQL and human-readable answers, automated chart generation and AI-written summaries for GenBI insights, and a semantic layer using MDL models to encode schemas, metrics, and joins. It integrates with many LLM providers and runtimes, including OpenAI, Azure, Google, Anthropic, Bedrock, Ollama, Databricks, Groq, and others. Supported data sources include major warehouses and databases such as BigQuery, Redshift, Snowflake, PostgreSQL, MySQL, ClickHouse, Oracle, Trino, DuckDB and Athena. The repo includes API endpoints and examples for embedding queries and charts into apps, installation and usage guides, configuration examples, and diagrams showing architecture and workflow.
Use Cases
Wren AI reduces the SQL learning curve by allowing stakeholders to ask questions in any language and receive decision-ready context in seconds via generated queries, visualizations, and summaries. The semantic layer helps keep outputs accurate and governed by encoding schema and metrics, improving reliability for analytics and reporting. Developers can embed query generation and charting in applications through provided APIs and configuration examples, enabling custom agents, chatbots, and SaaS features. The project supports multiple deployment options and many LLM and data source integrations, making it useful for teams wanting faster insights, consistent metric definitions, and easier access to analytics without requiring deep SQL expertise.

Please fill the required fields*