Dataherald vs Wren AI
Dataherald
github.comWren AI
getwren.aiSide by side
| Figure | Dataherald | Wren AI |
|---|---|---|
| Price from | — | $179/mo |
| Free plan | — | — |
| Free trial | — | Yes |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 4 |
| Spec score · AI Database Assistants | 7.7 (#11) | 7.6 (#13) |
| Spec score · AI SQL Generators | 7.7 (#10) | 7.5 (#15) |
| Deployment | The quick start describes self-hosting the engine with Docker, with Mongo running in a separate container for application data. | Deployments include managed cloud, private cloud, self-hosted, and fully air-gapped options; the security page says Cloud defaults to GCP us-east-4, with other regions on request. |
| Product | Dataherald is a natural language-to-SQL engine that exposes an API for asking questions about relational data in plain English. | Wren AI is a governed data agent that answers business questions, creates dashboards, and lets AI agents query data over MCP. |
| Security | The quick start says database connection data is encrypted before storage in MongoDB using an ENCRYPT_KEY and recommends changing the default MongoDB username and password. | The maker describes OIDC identity, project isolation, query-time row- or column-level controls where supported, and audit logging of SQL and activity. |
Plans
Wren AI
- Essential Cloud$179 a month
- Enterprise Cloud$559 a month
- Enterprise PlusPriced on request
- FreePrice not published
In their own words
Dataherald
Dataherald is an open-source natural language-to-SQL engine that exposes an API for asking questions about relational data in plain English. Its stated uses include helping business users query warehouses, embedding data Q&A in SaaS products, and creating ChatGPT plug-ins for proprietary data. The project targets developers building natural-language interfaces or contributing to the engine. Self-hosting uses Docker, with MongoDB in a separate container for application data. Listed warehouse connections are PostgreSQL, BigQuery, Databricks, and Snowflake. Included SQL-generation approaches are LangChain SQL Agent, LangChain SQL Chain, LlamaIndex SQL Generator, and Dataherald SQL Agent. A context store can include business and database details, validated question-and-SQL examples, and table information; active learning from usage is also described. An evaluator assigns confidence scores to generated SQL. The modular architecture allows implementations to be changed through .env configuration. Startup requires an OpenAI API key, organization ID, and encryption key. Connection data is encrypted before Mongo storage. The repository uses Apache-2.0 licensing.
Wren AI
Wren AI is a governed data agent for business questions, dashboard creation, and AI-agent data queries over MCP. Its MDL context layer models metrics, relationships, calculations, and approved data, and can be version controlled. The agent plans multi-step analysis, queries data, builds charts, and uses reusable Skills, shared Knowledge, and private project-scoped Memory. Users can describe dashboards, reports, or custom views in plain English, refine them conversationally, and save them as reusable Artifacts. Data connections include Snowflake, BigQuery, Databricks, Redshift, PostgreSQL, MySQL, SQL Server, Oracle, ClickHouse, Trino, Starburst, Athena, and CSV. Claude, ChatGPT, Claude Code, and compatible MCP clients can call Wren AI as a sub-agent. Deployment options include managed or private cloud, self-hosting, and air-gapped setups. The maker describes OIDC identity, project isolation, supported row- or column-level query controls, and audit logs, and labels its cloud SOC 2. Essential Cloud costs $179 a month, billed annually; a free plan is also listed.