Workbench Win

Statistician's Workbench for Windows โ€” structured recipe builder with AI-guided data preparation, and multi-database analytics. A Windows desktop application that connects to PostgreSQL, MySQL, SQL Server, and MS Access.

Learn More

What It Does

Workbench Win is a Windows desktop application that puts the full power of the Statistician's Workbench platform on your local machine. Connect to your databases โ€” PostgreSQL, MySQL, SQL Server, or MS Access โ€” import CSV, JSON, and Excel files, and build data preparation pipelines using a structured recipe editor or an AI assistant that guides you step by step. Run analytics without writing a line of SQL.

Your data stays on your machine. Workbench Win runs entirely locally โ€” no cloud, no server, no data leaving your network. Connect to local databases and files, process data on your own hardware, and keep everything under your control. AI-guided features can use cloud AI providers or a local LLM โ€” you choose. With a local LLM, no data ever leaves your machine.
๐Ÿงฉ

Structured Recipe Builder

Build data preparation pipelines step by step โ€” chain stages like filter, join, aggregate, pivot, and impute. Each stage previews its output so you can see exactly what your data looks like at every step.

๐Ÿค–

AI-Guided Recipes

An AI assistant guides you through building a recipe โ€” it sees your actual schema and data, then suggests which stages to use and how to configure them. Every suggestion is recorded alongside your decisions for a full audit trail. Connect to cloud AI providers or run a local LLM for total privacy.

๐Ÿ—„๏ธ

Multi-Database Support

Connect to PostgreSQL, MySQL, SQL Server, and MS Access. Browse schemas, preview tables, and run queries across all your databases from a single interface.

๐Ÿ“ฅ

File Import

Import CSV, JSON, and Excel files with automatic type detection. Preview data before import. Map columns, set types, and load directly into your database.

๐Ÿ“Š

Interactive Charts

Visualise results with bar charts, line charts, scatter plots, and histograms. Charts update as you refine your recipe โ€” instant feedback on every change.

๐Ÿ““

Jupyter Notebooks

Open any dataset as a Jupyter notebook for advanced analysis. Python, R, and SQL kernels โ€” write code, generate reports, and share results, all within Workbench Win.

๐ŸŒ

Multilingual UI

Full interface translation across multiple languages including Thai. Switch languages from the globe icon โ€” no restart required.

๐Ÿ”’

User Accounts & Groups

Multi-user support with role-based access control. Group admins manage their own users. Fine-grained permissions on datasets, recipes, and database connections.

๐Ÿ“ฆ

Single Installer

One .exe installer. Bundled Python runtime, all dependencies included. No Docker, no virtual environments, no command-line setup. Install and run.


How It Works

Workbench Win runs a local web server on your machine and opens your browser to the Workbench interface. Everything runs locally โ€” the backend, the database connections, the file processing, and the analytics engine:

StepWhat Happens
1. InstallRun the installer. It places the application, a bundled Python runtime, and all dependencies on your machine. A Start Menu shortcut and optional auto-start service are created.
2. LaunchDouble-click the desktop icon. A local uvicorn server starts on 127.0.0.1:8000 and your default browser opens to the Workbench login page.
3. ConnectAdd your database connections โ€” PostgreSQL, MySQL, SQL Server, or MS Access. Workbench Win uses native drivers (psycopg2, pymysql, pymssql, pymsaccess) to connect directly.
4. ImportDrag CSV, JSON, or Excel files onto the import panel. Preview the data, adjust column types, and load into your database โ€” or keep them as virtual datasets that query the file directly.
5. BuildCreate a recipe using the structured editor โ€” chain stages like Filter, Join, Aggregate, Pivot, and Impute โ€” or use the AI assistant, which suggests stages and configuration based on your actual data. Each stage shows a live preview of its output. Every AI suggestion is recorded, giving you a full audit trail of every decision.
6. AnalyseRun the recipe to produce a dataset. Chart it, export it to CSV/Excel, or open it as a Jupyter notebook for deeper analysis with Python or R.

Supported Databases

DatabaseDriverFeatures
PostgreSQLpsycopg2Full support โ€” schema browsing, table preview, SQL querying, recipe execution, data import/export
MySQL / MariaDBpymysqlFull support โ€” schema browsing, table preview, SQL querying, recipe execution
SQL ServerpymssqlFull support โ€” schema browsing, table preview, SQL querying, recipe execution. Feature-gated behind mssql_db licence flag
MS AccesspymsaccessSchema browsing, table preview, SQL querying. Read-only access to .accdb and .mdb files

Development Status

Version 0.0.12 โ€” in development. 0.0.11 (released 2026-07-24) delivered AI agents, chat, notebook import, mobile support, audio I/O, and MSSQL connectivity. 0.0.12 is the Recipe Redesign & Platform Polish milestone โ€” a complete rebuild of the recipe system with pipeline editor, SQL execution pushdown across five database backends, and platform-wide translation compliance. 15 of 21 tasks complete.

MilestoneVersionThemeStatus
0.0.1 โ€” Foundation0.0.9Dataset management, password policy, admin featuresโœ“ Released
0.0.2 โ€” Statistical Foundation0.0.10Core statistics, DuckDB engine, recipes, sharing, multilingual UI, database connectionsโœ“ Released
0.0.3 โ€” AI Agents & Collaboration0.0.11Chat agents, AI providers, notebook import, mobile support, audio I/O, MSSQL, Golden Screwdriverโœ“ Released
0.0.4 โ€” Recipe Redesign & Platform Polish0.0.12Pipeline editor, dataset transforms, SQL execution engine (5 backends), recipe sharing, translation compliance๐Ÿ”„ In Progress (15/21)
0.0.5 โ€” Production Readiness0.0.13Security audit, performance optimisation, activity logs, comprehensive testing, documentation, backup & recovery๐Ÿ“‹ Planned
๐ŸŽฏ Current focus: Recipe Redesign (0.0.4). The recipe system is being rebuilt with a master-detail layout, three-component pipeline editor, and a universal SQL execution engine that compiles operations for DuckDB, PostgreSQL, MySQL, MSSQL, and MS Access โ€” with automatic fallback to pandas when a backend lacks native support for an operation.

Licensing

Workbench Win is part of a family of Workbench products:

ProductLicenseNotes
WorkbenchOpen SourceThe community edition. Full platform โ€” PostgreSQL backend, recipe engine, statistics, charts, multilingual UI. Free to use, modify, and self-host.
Workbench-BECommercialThe Business Edition. Adds multi-user with role-based access control, group administration, MSSQL and MS Access connectivity, Jupyter notebooks, and priority support.
Workbench WinLicensed (free)The Windows desktop application. A licence key is required and is included with the download at no cost. One version โ€” no tiers, no feature gating. Every user gets the full platform.
Workbench MacPlannedThe macOS desktop application โ€” same easy-install approach as Workbench Win. Under consideration. As with Workbench Win, technically-inclined users may prefer to run the open-source Workbench directly.
Workbench Win: one version, free, no catch. The licence key activates the software and identifies your installation for support purposes. It does not expire, does not limit features, and does not require renewal. Install, enter the key, and the full Workbench Win is yours.

System Requirements

ComponentRequirement
Operating SystemWindows 10 (21H2+) or Windows 11
Architecturex86-64 (64-bit)
Memory4 GB RAM minimum, 8 GB recommended
Disk Space~500 MB for application + bundled runtime
BrowserAny modern browser โ€” Chrome, Edge, Firefox. The interface opens automatically in your default browser.
Database (optional)PostgreSQL 12+, MySQL 8+, SQL Server 2019+, or MS Access 2010+ (.accdb / .mdb)