Dataset-generator is an open-source Data & Analytics tool that creates realistic datasets for demos, learning, and dashboards. It offers real-time data previews and exports to CSV or SQL.
Dataset-generator is an open-source AI tool designed to create realistic datasets for various purposes, including demos, learning, and building dashboards. It features a conversational prompt builder that allows users to define business types, schema, and row counts. The tool provides real-time data previews directly in the browser and supports exporting data as CSV (single file or multi-table ZIP) or SQL inserts. A key differentiator is its two-stage process: it uses large language models to generate detailed data specifications and then uses Faker.js locally to create unlimited realistic data rows based on those specs. This approach means users only incur LLM costs for the initial spec generation, with subsequent data downloads being free. It also integrates with Metabase for one-click data exploration.
Best used for
Ideal for data scientists and developers who need to quickly generate realistic datasets for testing applications, populating demo environments, and creating data for dashboard prototypes. Especially valuable for those seeking to simulate complex business data without using real-world sensitive information, leveraging AI for schema generation and local tools for data population.
The tool uses a two-stage process. LLMs are only called once to generate the data specification (schema, rules). All subsequent data rows are generated locally using Faker.js, meaning you only pay for the initial preview/spec generation, not for downloading large datasets.
Can I use other LLM providers besides OpenAI?
Yes, while the web version defaults to OpenAI, running the tool locally allows you to use LiteLLM for multi-provider LLM support. You can configure API keys for providers like Anthropic and Google in your .env file.
What are the prerequisites for running Dataset-generator locally?
To run the tool locally, you need Node.js (version 18 or later) and an OpenAI API key. Docker is optional but recommended if you want to spin up Metabase or use LiteLLM for multi-provider LLM support.
Shypd.aiThe largest open index of AI tools
