Back to directory

datasette-agent

A Datasette plugin that adds an LLM-powered chat assistant for exploring a Datasette instance's databases and tables, plus background agents that write exploration reports.

datasette-agent

datasette-agent is a plugin that adds an LLM-powered chat assistant to a Datasette instance, reachable at /-/agent. It uses the datasette-llm plugin to call language models, and a configured default model can be overridden per conversation from a model picker that lists only models with an available API key that can also call tools.

A conversation's model choice is fixed for that conversation's lifetime; starting a new chat is the way to switch models. The available model list and the current conversation's model are also exposed as JSON, and conversations can be created programmatically with a specific model. Explore with AI agent entries in the database and table menus launch a background agent that explores the selected data and writes a report, and background agents can also be started directly from a dedicated page.

It is installed alongside Datasette and is Apache-2.0 licensed.

More in Databases

See all 294
  • SQLBraid

    clickin.github.io

    A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.

  • A SQL-style query language and toolchain for the Qdrant vector database, covering dense, sparse and hybrid search, filtering and multitenancy, with the same grammar running from a CLI, Python, Node.js, Rust, WebAssembly and an in-process edge engine.

  • Fast Knowledge

    github.com

    A self-hosted, Java-based knowledge base for small and mid-sized organizations, turning internal documents into a searchable, question-answerable and audit-exportable knowledge asset with hybrid retrieval and Docker deployment.