Chion vs Dataherald
Chion
chion.aiDataherald
github.comSide by side
| Figure | Chion | Dataherald |
|---|---|---|
| Price from | $29/mo | — |
| Free plan | — | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 4 | 0 |
| Spec score · AI SQL Generators | 8.2 (#4) | 7.7 (#10) |
| What it does | Chion turns plain-English questions about PostgreSQL into code-validated read-only SQL and interactive D3 charts, with the SQL shown under each chart. | Dataherald is a natural language-to-SQL engine that lets users ask questions in plain English about structured or relational data through an API. |
Plans
In their own words
Chion
Chion turns plain-English questions about PostgreSQL into code-validated, read-only SQL and interactive D3 charts, displaying the SQL beneath each chart. It connects directly to PostgreSQL without ETL or a warehouse copy, supporting Amazon RDS, Azure Database for PostgreSQL, Google Cloud SQL, Neon, Supabase, and self-hosted PostgreSQL. Validators reject statements that are not read-only SELECT queries before database execution. Results are limited to 1,000 rows or 12,000 cells. Eight built-in chart types include line, area, bar, and animated bar-race formats. Saved queries can become portable SQL skill files for Claude Code and Codex. Chion runs in the cloud through the web. Starter costs $29/seat/mo, Pro $99/seat/mo, and Max $299/seat/mo, each with a seven-day trial; Enterprise uses custom per-team pricing. Credentials are encrypted in an AES-256-GCM vault, while Chion says it is not SOC 2 certified and does not support HIPAA workloads.
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.