Who it is forAn analyst who wants teammates to explore results without touching Python.
The problemSharing notebook results usually means static screenshots or rebuilding the analysis in Streamlit.
The outcomeA running web app where UI elements drive the analysis and the code stays hidden and uneditable.
What you need first
- Python and pip or conda
- Optional: marimo[recommended] for SQL cells, AI completion and more
- Optional: your own API keys or a local model for AI features
Steps
- Install with
pip install marimo - Create or edit a notebook with Marimo edit and bind sliders, dropdowns or tables to Python values; dependent cells rerun automatically
- Run it as an app with
marimo run your_notebook.py - Use the slides layout if you want to present it
- Share a cloud copy through molab when teammates cannot run it locally
Prompt for your agent
With marimo-team/marimo, add a slider and a dropdown to <notebook.py> that filter <dataset> and update the chart, then serve it with `marimo run your_notebook.py` and give me the local URL.
Caveat. This card is written from the marimo-team/marimo README, not from a test run by Deduped. Before you start, make sure you have Python and pip or conda. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for marimo-team/marimo and "Turn an analysis notebook into an interactive web app"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer