DBQuill vs Snowflake Cortex Search

DBQuill is a free, open-source, self-hosted Windows desktop app for asking database questions in natural language, reviewing operations, and viewing charts. It supports SQLite directly and provides read paths for MySQL 8.4 and PostgreSQL 17. You can attach CSV or.xlsx files, which DBQuill converts into a local SQLite database; legacy.xls files are not supported. Write operations require validation, a change preview, and explicit confirmation, while remote DDL is blocked. Reads are limited to one statement and bounded rows. SQLite reads use physical read-only connections and query_only. DBQuill accepts an OpenAI-compatible text-model endpoint without requiring a particular vendor. Credentials, model profiles, sessions, audit records, and uploads are stored locally outside the source tree. Audit records retain controlled metadata and hashes rather than raw prompts, SQL, credentials, or result rows. The current target is Windows 10 or 11 x64 with CPython 3.12 and Microsoft Edge WebView2 Runtime. Distribution is source-first, without a signed native installer. The listed plan is free.

Snowflake Cortex Search has no write-up on Specifiction yet; its figures are above.