Skip to main content
AI Inspiration World
AI AppsAI SkillsAI GamesAI Short Films

⌕
EN|中文
About中
AI AppsAI SkillsAI GamesAI Short FilmsAbout
Home/AI Apps/llm-tools-datasette
AI Apps · AI Tools · Developer Toolsllm-tools-datasette

Added Oct 21, 2026

llm-tools-datasette

A plugin for the LLM command-line tool that lets a model query a Datasette instance you point it at, read its tables and run SQL.

Creator
Simon Willison
Pricing
Not confirmed
View work and source ↗

What it is

llm-tools-datasette is a plugin by Simon Willison for his LLM command-line tool. In the README's words, it exposes Datasette instances to LLM as a tool. Once installed, you give it a Datasette URL and the model can look at the tables, write SQL to query them, and answer your question from the results. What sets it apart is that every query goes through Datasette's own API, so the model can only reach what that Datasette already allows.

Who it's for:Developers and data hobbyists who already keep data in Datasette and want a model to help query it. Readers who don't write code won't get much from it.

Before you start: You need Python 3.11 or later and the LLM command-line tool; install with llm install llm-tools-datasette. Model accounts and costs depend on which model you use in LLM. SQL queries are sent in the URL to the Datasette you choose and may end up in that server's logs, and the results and table structure go to your chosen model. The plugin doesn't handle sign-in; whether access is read-only and what data is visible depends on that Datasette's permissions, so check them before pointing it at sensitive data. Apache-2.0 licensed.

Based on the project's public documentation. Not tested by AI Inspiration World.

Source

https://github.com/simonw/llm-tools-datasette ↗
How rankings work →
Is this your product? Claim this profileSuggest an update
AI Inspiration World logo: aiw. picked by humansAI Inspiration World logo: aiw. picked by humansAI Inspiration World

Check in daily. The newest in AI lives here.

Updated every day · Latest arrival: Oct 21, 2026

Site version: Oct 21, 2026

About·Methodology·Trust & Safety·@AIInspoWorld