Lightnews — Scholar-powered news

Ditch Excel for This Marimo Finance Tool

marimo @marimo.io · 7d

Build live and customizable data tools with marimo's built-in data editor, like this financial tracker:

youtube.com/shorts/eTPd...

Feel free to play around with the code/tool here: https://molab.marimo.io/notebooks/nb_Wq6zCfAURWbbd7YdvSVLZq

Making marimo better for humans and agents

1 1

marimo @marimo.io · 9d

In the coming weeks, we will have a lot more to say about how marimo is uniquely well-suited to empower both agents and humans to rapidly create production-ready data apps and pipelines ... see our latest newsletter for a sneak peek!

marimo.io/blog/newsle... (n/n)

Newsletter 18

marimo @marimo.io · 9d

Previously, agents like Claude Code could already execute marimo notebooks as scripts to get feedback on the correctness of their code.

With marimo check, agents can get additional feedback without running a single line of code, empowering them to self-correct on the fly. (5/n)

marimo @marimo.io · 9d

Developers and agents prefer marimo to Jupyter because it's code-first and productionizable ...

... while agents wielding marimo make Python accessible to non-technical users who were previously limited by Looker's inflexible UI (4/n)

marimo @marimo.io · 9d

Companies large and small are replacing legacy data tools with AI-native, workflows built on marimo because of our code-first and productionizable design

With agents, marimo lets companies go instantly from prompt to data app, pipeline, LLM eval notebook, and more (3/n)

marimo check: a notebook linter for agents and humans

marimo @marimo.io · 9d

marimo.io/blog/marimo... (2/n)

Introducing "marimo check", a linter that enables agents and humans alike to write high-quality notebooks, pipelines, and apps with marimo

marimo @marimo.io · 9d

Introducing `marimo check`: a linter that gives agents the feedback they need to write production-ready data apps, pipelines, and notebooks with marimo. (1/n)

1 1 5

marimo @marimo.io · 9d

We made something special for Django users, especially those who want to go beyond the standard shell/admin interface.

Learn all about it here:
youtu.be/ksGIAy2s_5k

AI Coding & Agents Happy Hour · Luma

marimo @marimo.io · 12d

You can now add your notebook to our website's gallery through the Secret button on the top right of your molab notebook.

2

marimo @marimo.io · 15d

We're having our first ever in person meetup on October 7th from 6-7 PM in San Francisco as part of SF Tech Week. Join the marimo team and community for a casual chat about AI-assisted coding and agents!

RSVP: luma.com/pp27h5fo

Join us for a casual hour of chatting about AI-assisted coding and agents.

luma.com

1 6

marimo @marimo.io · 16d

We've all seen dataframe spaghetti code out there.

But the remedy ... is pretty easy: just start using the pipe method!

The moment you see the `.pipe()` in action, you'll never want to write pipelines without it. See the reason why here:
www.youtube.com/watch?v=J0P...

The One Trick That Fixes Pandas Spaghetti Code

In this video I am going to show you 6 reasons why the `.pipe()` method basically fixed all dataframe code out there. Python notebooks turn messy very quickl...

Release 0.16.0 · marimo-team/marimo

marimo @marimo.io · 19d

We also have an agent sidebar ready for alpha testing. Connect marimo notebooks to AI coding assistants like Claude Code or Gemini CLI through the new Agent sidebar. You can learn more in the full release notes: github.com/marimo-team...

This release brings multi-cell AI code generation and marimo check for static code analysis, along with preview features for AI agents. Highlights Generate multiple cells with AI You can now genera...

github.com

marimo @marimo.io · 19d

Release 0.16.0 delivers multi-cell AI code generation and common error detection/reporting before runtime.

The "Generate with AI" feature now can create multiple cells at once and run marimo check to identify issues such as multiple definitions, circular dependencies, and syntax errors.

17 marimo features to boost Python productivity

marimo @marimo.io · 23d

There's *a lot* of feature's that we're proud of.

But some are less well known than others, so we made a video!

youtu.be/OM7utZeQ1GY

All of these features really do boost your productivity.00:00 Productivity00:42 marimo in the terminal 03:19 LLM via --watch flag05:10 The "new" command 06:2...

Release 0.15.3 · marimo-team/marimo

1 3

marimo @marimo.io · 26d

Thanks to Zane, Thomas, Will, Matthew, and David for making their first-ever contribution for this release!

Please review the release notes for more details and stay tuned for more improvements to AI-assisted coding: github.com/marimo-team...

This release focuses on AI enhancements and developer experience improvements, with better ways to provide context to AI chat and real-time feedback during package installation. Internal messaging ...

github.com

marimo @marimo.io · 26d

Release 0.15.3 provides real-time feedback when installing packages. You can now see the live installation logs without the terminal. We've also included the ability to reference files, cell outputs, and media to AI for better assistance.

1 2 5

marimo @marimo.io · 28d

You can also try it out yourself by going here:
molab.marimo.io/notebooks

molab

molab is a cloud-hosted marimo notebook workspace that lets you rapidly experiment on data with Python and SQL

Generate full notebooks from a dataset.

marimo @marimo.io · 28d

Check our latest YT video for a full demo:
youtu.be/JQzSqMuTXOo

To try out this new feature go to https://molab.marimo.io/.00:00 Setup01:05 First notebook 02:04 Second notebook

marimo @marimo.io · 28d

We just upgraded molab. You can now attach a file to a prompt to generate a full notebook from scratch that analyses the file you just uploaded!

1 1 2

marimo @marimo.io · 29d

Check out the blog for usage tips and let us know what AI/ML tool you'd like to use with marimo next. marimo.io/blog/claude...

marimo @marimo.io · 29d

Pair with Claude Code to write marimo notebooks in only three lines.

Claude can easily understand your code in marimo via our Python file format and dataflow graph, propelling the shift from prompt engineering to context engineering.

CodeCut is a site for data scientists focused on modern tools that boost productivity and improve their workflow. Curated by Khuyen Tran, it features hands-on tutorials, insightful blogs, and practical guides to help you work smarter.

marimo @marimo.io · Sep 9

📬 Subscribe to the newsletter: bit.ly/4p4WfZX

Home

codecut.ai

marimo @marimo.io · Sep 9

Learning is better when it’s interactive.

The CodeCut newsletter by Khuyen Tran delivers Python and AI tips, 3 times a week, and now each issue includes a "Run Code" button. With one click, you can launch a molab notebook and experiment with the examples directly in your browser.