Simon Willison releases Datasette Agent for SQL data analysis
simon willison launched datasette agent, an extensible ai assistant that queries sqlite databases using gemini 3.1 flash-lite and supports visualization via plugins.
simon willison announced the first release of datasette agent, an extensible ai assistant that integrates his llm python library with the datasette data exploration tool. the agent provides a conversational interface for asking questions about sqlite data, using gemini 3.1 flash-lite to write and execute queries. the launch includes three plugins: datasette-agent-charts for visualization, datasette-agent-openai-imagegen for image generation, and datasette-agent-sprites for code execution in a fly sprites persistent sandbox. the project supports local open-weight models like gemma-4-26b-a4b and is designed to be extended with new tools created by ai coding assistants like claude code.