Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Marimo pair – Reactive Python notebooks as environments for agents

github.com

Post reply on HN
Print view View original

31–40 of 40 posts

Re: Show HN: Marimo pair – Reactive Python notebooks as environments for agents

#33

Post by rasmus1610 »

This is such an exciting direction :)

Jeremy Howard from fast.ai/answer.ai also works on similar stuff with solveit (https://solve.it.com) and ipyai (https://github.com/AnswerDotAI/ipyai)

I think it will be very interesting to see what this enables

Re: Show HN: Marimo pair – Reactive Python notebooks as environments for agents

#34

Post by data-ottawa »

crashabr wrote: post #27
data-ottawa wrote: post #26

Earlier quoted context omitted.

I started using marimo for the reactive execution, after being spoiled by Observable and Pluto.jl Being able to plug directly into Altair charts and tables was a huge boon. Then I discovered anywidget, which has been a game changer. Now I use Claude to generate anywidgets for controls I need, and just focus on the heavy lifting with python, it's great. Being able to just have this all run in one flow with pair should…

The visual cleaning idea is really interesting. Would you mind sharing more details?

It's nothing revolutionary.

It's essentially a table layout with a plus button at the bottom. When you click it adds a new step as a row, then you pick the operation, the input columns and output column name.

If you want to add another step you click the plus again and add another row the same way. Each row can access any table field or output field defined above it in the DAG.

Then in Python a for loop runs over the steps in order and updates the data frame in place (well, in function, returning the new one). It uses a dictionary of function mappings and resolves input fields with kwargs.

Re: Show HN: Marimo pair – Reactive Python notebooks as environments for agents

#35

Post by midnightn »

The reactive execution model as agent memory is clever — I ran into similar tradeoffs building a multi-agent trading system where each agent needs isolated state across cycles. Ended up using a persistent store (BigQuery) rather than in-process memory, but the appeal of having the runtime itself be the memory is that you get reproducibility for free.

Re: Show HN: Marimo pair – Reactive Python notebooks as environments for agents

#36

Post by llamavore »

mscolnick wrote: post #8
llamavore wrote: post #4

Looks cool. I love notebooks. I built something similar with just plain cli agent harnesses for Jupyter a while back. It supports codex subscriptions and pi, (used to support Claude subs, might still be okay since I didn’t modify the system prompt). Has some bugs and needs some work but getting help and code changes inline in Jupyter is way better than copy pasta hard to select text from cells and cell output all day…

This is cool. Do you still use this? There has been ideas thrown around to add "prompt" cells to marimo that can similarly create outputs or downstream cells and the prompts are serialized to the notebook py file and part of the DAG.

Yeah I use it myself when I need to quickly debug something in Jupyter because I can just pip install cleon anywhere and then do @ question to get codex involved.

I took Jeremy’s solveit course and built this in homage to the concept of AI agent within Jupyter.

Keen to collaborate with anyone if they want to take this paradigm further.

Re: Show HN: Marimo pair – Reactive Python notebooks as environments for agents

#37

Post by llamavore »

llamavore wrote: post #36
mscolnick wrote: post #8

Earlier quoted context omitted.

This is cool. Do you still use this? There has been ideas thrown around to add "prompt" cells to marimo that can similarly create outputs or downstream cells and the prompts are serialized to the notebook py file and part of the DAG.

Yeah I use it myself when I need to quickly debug something in Jupyter because I can just pip install cleon anywhere and then do @ question to get codex involved. I took Jeremy’s solveit course and built this in homage to the concept of AI agent within Jupyter. Keen to collaborate with anyone if they want to take this paradigm further.

I will add I’m sad to see Anthropic go anti-community on their Claude subscription usage but since Codex works in pi then using pi as the underlying harness is probably the best thing to do. I did use open source codex rust in cleon to easily bring that into python directly. Big thanks and props to OpenAI for building their coding harness in rust and doing it open source.
Post reply on HN