A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
marimo is a reactive Python notebook in which changing a cell or interface control automatically updates dependent code, keeping code and outputs consistent. It is used for reproducible data work, SQL queries, experiments, scripts, interactive applications, and deployable web apps. The catalogue contains instructions and skills for working with marimo.
This repository also configures its own agents. See what marimo tells them →
Skill Claude CodeCodex
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
Skill Claude Code
Curate descriptions and provider-specific reasoning options and token limits in packages/llm-info/data/models.yml using models.dev, OpenRouter, and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or curate descriptions after running pnpm sync-models.