DBQuill
github.com
What it is
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.
Spec sheet
- Purpose
- DBQuill is an open-source, local-first AI database agent for asking questions in natural language, reviewing database operations, and viewing charts.Read 4 Oct 2026 · github.com
- Intended users
- The project describes natural-language querying and controlled updates for people working with SQLite, MySQL, or PostgreSQL databases and tabular files.Read 4 Oct 2026 · github.com
- Security
- Reads are single-statement and row-bounded, and SQLite reads use physical read-only connections plus query_only.Read 4 Oct 2026 · github.com
- Support
- Support guidance directs users to the installation guide, diagnostics, and GitHub issues; no response-time or bounty guarantee is offered for security reports.Read 4 Oct 2026 · github.com
- Audit privacy
- Audit records retain controlled metadata and hashes rather than raw prompts, SQL, credentials, or result rows.Read 4 Oct 2026 · github.com
- Database support
- It supports SQLite and provides read paths for MySQL 8.4 and PostgreSQL 17.Read 4 Oct 2026 · github.com
- Distribution
- DBQuill is source-first and does not yet provide a signed native installer.Read 4 Oct 2026 · github.com
- File imports
- Users can attach CSV or .xlsx files, which DBQuill converts into a local SQLite database; legacy .xls is not supported.Read 4 Oct 2026 · github.com
- Local data
- Database credentials, model profiles, sessions, audit records, and uploads are stored locally outside the source tree.Read 4 Oct 2026 · github.com
- Model compatibility
- DBQuill accepts an OpenAI-compatible text-model endpoint and does not require a specific model vendor.Read 4 Oct 2026 · github.com
- Other platform limits
- macOS, Linux, Windows on ARM, and other Python versions are not release targets yet.Read 4 Oct 2026 · github.com
- Supported platform
- The current release target is Windows 10 or 11 x64 with CPython 3.12 and Microsoft Edge WebView2 Runtime.Read 4 Oct 2026 · github.com
- Write controls
- Writes require validation, a change preview, and explicit confirmation; remote DDL is blocked.Read 4 Oct 2026 · github.com
Plans and prices
Strong points and limits
Strong points
- Free and open source
- Natural-language queries and write operations
- CSV and .xlsx imports
- Validation and previews for writes
- Local storage and controlled audit metadata
Limits
- Windows-only release target
- Legacy .xls files unsupported
- No signed native installer yet
- Remote DDL is blocked
Who it suits
It suits people working with SQLite, MySQL, or PostgreSQL databases and tabular files who want natural-language querying, controlled updates, and charts on Windows.
Verdict
DBQuill combines natural-language database work, guarded writes, and result visualizations in a self-hosted Windows application. Check its Windows, Python, WebView2, and file-format requirements before adopting it.
Where Specifiction places it
- AI Database Assistants#12 of 217.6