bbolt vs DuckDB UI

bbolt is a maintained fork of Bolt, providing Go applications with an embedded key-value store instead of a full database server. It keeps the database in one file, representing a consistent snapshot of its data. Key/value pairs are arranged in buckets, which can be nested, and bucket keys are stored in byte-sorted order. The library supports serializable ACID transactions: one read-write transaction at a time, alongside multiple concurrent read-only transactions.

A read-only transaction can create a consistent hot backup without blocking other database reads and writes. bbolt exposes operation statistics that can be logged or sent to a service such as statsd. The project describes it as a fit for read-intensive workloads and range scans, while warning that random writes can be slow. The database file has an exclusive write lock, so multiple processes cannot share it for writing; read-only mode permits multiple readers. The project documents gomobile bindings for iOS and Android, as well as Windows, macOS and Linux support. It is free under the MIT license, with no paid support plan listed.

DuckDB UI is a free browser interface for a local DuckDB instance, added through the ui extension. Start it with `duckdb -ui` or `CALL start_ui()`; it opens in the default browser and is served by an HTTP server embedded in DuckDB, available by default at `http://localhost:4213`. The interface includes a SQL notebook with autocomplete and keyboard shortcuts, a catalog browser, a table explorer with column statistics, and a results viewer with sorting and filtering. The native DuckDB process gives it access to local cores, memory, and files. Queries run locally by default, and queries and data stay on the computer. Connecting to MotherDuck is optional and requires signing in. The UI is built and maintained by MotherDuck. The local server retrieves interface files from ui.duckdb.org, so alternate configured URLs should be trusted because the application can access loaded DuckDB data. The UI cannot be run directly against a read-only database and does not currently support windows_arm64.