Skip to content

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.

Update marimo-pair docs to mention molab (#9436)

vincent d warmerdam3f10cc6483f7
diff --git a/docs/_static/marimo-pair-molab.png b/docs/_static/marimo-pair-molab.png
new file mode 100644
index 0000000000..2b2420d13f
Binary files /dev/null and b/docs/_static/marimo-pair-molab.png differ
diff --git a/docs/guides/generate_with_ai/marimo_pair.md b/docs/guides/generate_with_ai/marimo_pair.md
index 0e177f065e..52dbd29a98 100644
--- a/docs/guides/generate_with_ai/marimo_pair.md
+++ b/docs/guides/generate_with_ai/marimo_pair.md
@@ -40,3 +40,15 @@ Then pair on your first notebook by pasting the following in your agent CLI:
```
/marimo-pair pair with me on my_notebook.py
```
+
+## Sandbox with molab
+
+You can also connect to marimo notebooks running on [molab](https://molab.marimo.io/notebooks). This gives you a free sandbox for your agent and also makes it easy to share your work afterwards.
+
+To connect an agent, start a notebook on molab and open the actions panel in the upper right corner. From this menu you need to click "Pair with an agent".
+
+<div align="center">
+ <img src="/_static/marimo-pair-molab.png" alt="Screenshot of a molab notebook showing the option to pair with an agent from the actions panel"/>
+</div>
+
+This will open up a menu with all the instructions to connect your local agent. You can then use your agent from the terminal as normal, but all the Python code would be written into the notebook in the molab sandbox.