Datasette Agent ships conversational SQL interface
Extensible AI assistant for Datasette that converts natural language to SQLite queries and charts via plugin system; runs on Gemini 3.1 Flash-Lite or local models like gemma-4-26b.
May 22, 2026
Summary
Eliminates manual SQL writing for data exploration workflows. Plugin architecture lets you inject domain-specific tools (image generation, code execution, charting) without forking core—critical for teams building on Datasette infrastructure.
Why it matters
Eliminates manual SQL writing for data exploration workflows. Plugin architecture lets you inject domain-specific tools (image generation, code execution, charting) without forking core—critical for teams building on Datasette infrastructure.
Implementation verdict
Replaces manual SQL + charting workflows for Datasette users. Requires Datasette instance + Claude/OpenAI/local LLM with reliable tool calling. Ready now for exploration; production viability depends on query reliability against your schema. Start with the live demo at agent.datasette.io to validate behavior.
Sources
- 1.Datasette Agent provides a conversational interface for asking questions of the data you have stored in Datasette
- 2.Add the datasette-agent-charts plugin and it can generate charts of your data as well
- 3.The live demo runs on Gemini 3.1 Flash-Lite—it's cheap, fast and has no trouble writing SQLite queries
- 4.like the rest of Datasette, it's extensible using plugins
- 5.Claude Code and OpenAI Codex are both proving excellent at writing plugins
Dev Signal
Get briefs like this in your inbox — free, 3x a week.
100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.