marimo

e); (2) the ability to write Marimo notebooks. When prompted, the LangGraph agent will run exploratory data analysis using database query tools. Then, it creates a polished Marimo notebook that's presented to the user in read-only mode. This project intentionally hides the Marimo edit mode. That means that the end user only ever sees a finished, read-only data app. Ease of use and trust in AI output were the main drivers behind this decision. 4 data sources are currently supported: Snowflake, BigQuery, Postgres, and Metabase. The code for the database query tools was derived from Google's open source MCP Toolbox for Databases. There is currently no support for MCP. Instead, data query tools are hardcoded. This decision was made to ensure high quality AI queries and limit tool bloat. This is an early stage project, and is configured to only run locally at this time. [1] https://github.com/marimo-team/marimo [2] https://news.ycombinator.com/item?id=47678844

ll packages (marimo records these actions in the associated notebook, which is just a Python file). The agent can even manipulate marimo's user interface — for fun, try asking your agent to greet you from within a pair session. The agent effects all actions by running Python code in the marimo kernel. Under the hood, the marimo pair skill explains how to discover and create marimo sessions, and how to control them using a semi-private interface we call code mode. Code mode lets models treat marimo as a REPL that extends their context windows, similar to recursive language models (RLMs). But unlike traditional REPLs, the marimo "REPL" incrementally builds a reproducible Python program, because marimo notebooks are dataflow graphs with well-defined execution semantics. As it uses code mode, the agent is kept on track by marimo's guardrails, which include the elimination of hidden state: run a cell and dependent cells are run automatically, delete a cell and its variables are scrubbed from memory. By giving models full control over a stateful reactive programming environment, rather than a collection of ephemeral scripts, marimo pair makes agents active participants in research and data work. In our early experimentation [4], we've found that marimo pair accelerates data exploration, makes it easy to steer agents while testing research hypotheses, and can serve as a backend for RLMs, yielding a notebook as an executable trace of how the model answered a query. We even use marimo pair to find and fix bugs in itself and marimo [5]. In these examples the notebook is not only a computational substrate but also a canvas for collaboration between humans and agents, and an executable, literate artifact comprised of prose, code, and visuals. marimo pair is early and experimental. We would love your thoughts. [1] https://github.com/marimo-team/marimo-pair [2] https://marimo.io/blog/marimo-pair [3] https://github.com/marimo-team/marimo [4] https://www.youtube.com/watch?v=VKvjPJeNRPk [5] https://github.com/manzt/dotfiles/blob/main/.claude/skills/m...

view to be "real devs". The question of whether marimo will catch on has already been resolved :) https://github.com/marimo-team/marimo

s a modern notebook for modern data workflows; we also built molab on a modern tech stack: - Notebook dependencies are managed by uv, enabling lighting-fast package installation (thanks to uv’s cache and more generally its performant implementation). uv makes it easy to run molab notebooks locally, too: uvx marimo edit <notebook-url> brings the notebook down to your machine. - Persistent storage is powered by R2, Cloudflare’s zero-egress object store. - We use Pydantic logfire to monitor our deployment. - While our implementation is agnostic to the compute backend (stay tuned!), we’re currently running on Modal for fast startups (not to mention a slick developer experience). Modal sandboxes make it easy for us define containers at runtime, containing notebook code and their dependencies. (Shout out to Eric Zhang from Modal for helping us get started.) molab is free to use, as long as usage is reasonable. Our goal is to make is as easy as possible for our community to use marimo notebooks. Finally, learn more at our announcement blog: https://marimo.io/blog/announcing-molab If this interests you, please give molab a shot and please share feedback — here or on Discord (https://marimo.io/discord). P.S. This is not our commercial product, this is really just for our community. [1] https://github.com/marimo-team/marimo [2] https://github.com/googlecolab/colabtools/issues?q=is%3Aissu...

ASM with pyodide. https://github.com/simonw/datasette-lite pygwalker: https://github.com/Kanaries/pygwalker .. https://news.ycombinator.com/item?id=35895899 How do you record manual interactions with ui controls and spreadsheet grids to code for reproducibility? > "Generate code from GUI interactions; State restoration & Undo" https://github.com/Kanaries/pygwalker/issues/90 > The Scientific Method is testing, so testing (tests, assertions, fixtures) should be core to any scientific workflow system. ipytest has a %%ipytest cell magic to run functions that start with test_ and subclasses of unittest.TestCase with the pytest test runner. https://github.com/chmp/ipytest How can test functions with assertions be written with Probly?

c assumes the notebook was meant to be run top-down, which is usually but not always true [3]. It can convert many notebooks, but there are still some edge cases. We implemented the filesystem mount using our own FUSE-like adapter that links the GitHub repository’s contents to the Python filesystem, leveraging Emscripten’s filesystem API. The file tree is loaded on startup to avoid waterfall requests when reading many directories deep, but loading the file contents is lazy. For example, when you write Python that looks like ```python with open("./data/cars.csv") as f: print(f.read()) # or import pandas as pd pd.read_csv("./data/cars.csv") ``` behind the scenes, you make a request [4] to https://raw.githubusercontent.com/<org>/<repo>/main/data/car.... Docs: https://docs.marimo.io/guides/publishing/playground/#open-no... [1] https://github.com/marimo-team/marimo [2] https://news.ycombinator.com/item?id=39552882 [3] https://blog.jetbrains.com/datalore/2020/12/17/we-downloaded... [4] We technically proxy it through the playground https://marimo.app to fix CORS issues and GitHub rate-limiting.

keeping marimo free, open-source, and permissively-licensed. Just as we’re making marimo a great programming environment for working with data, one day we'd like to make a great platform for working with data. Our company will eventually offer a product that optionally integrates with marimo and other tools we develop, but the tools themselves will always be open source and permissively licensed. For now, our fundraise lets us fully commit to building the marimo notebook. It also gives us the room to explore building other tools for working with data. We’ve come a long way since our ShowHN, but there’s still a lot more we want to build. We're currently brainstorming our roamdap to V1 and would love your feedback: https://github.com/marimo-team/marimo/discussions/2899