We’ve been exploring a similar direction too, but focused on a plain REPL rather than notebook semantics or explicit session management beyond interrupts and restarts. It seems like the tradeoff is between keeping the interaction model simple and the context small, versus introducing notebook structure earlier and having the model work toward an artifact at the same time as it iterates and explores. Curious how you think about that balance?
I am a big fan of Marimo and was trying to use it as my agent’s “REPL” a while back, because it’s naturally so good at describing its own current state and structure. It made me think that it would make a better state-preserving environment for the agent to work. I’m very excited to play with this.
One of the authors here, happy to answer questions.
Building pair has been a different kind of engineering for me. Code mode is not a versioned API. Its consumer is a model, not a program. The contract is between a runtime and something that reads docs and reasons about what it finds.
We've changed the surface several times without migrating the skill. The model picks up new instructions and discovers its capabilities within a session, and figures out the rest.
You could wrap pyobject via a proxy that controls context and have AI have a go at it.
You can customise that interface however you want, have a stable interface that does things like
`
proxy.describe()
proxy.list_attrs()
proxy.get_attr("columns")
proxy.sample_rows(limit=5)
proxy.children(path=["model", "layers"], limit=10)
`
This way you get a general interface for AI interacting with your data, while still keeping a very fluid interface.
Built a custom kernel for notebooks with PDB and a similar interface, the trick is to also have access to the same API yourself (preferably with some extra views for humans), so you see the same mediated state the AI sees.
By 'wrap' I mean build a capability-based, effect-aware, versioned-object system on top of objects (execs and namespaces too) instead of giving models direct access. Not sure if your specific runtime constraints make this easier or harder. Does this sound like something you'd be moving towards?
Codex just picks it up. The surface is basically a guarded object model, so pandas/polars-style operations stay close to the APIs the model already knows. There's some extra-tricks but they're probably out of scope for an HN comment.
In practice, Pandas/Polars API would lower to:
proxy -> attr("iloc") -> getitem(slice(1,10,None))
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.
Very cool!
We’ve been exploring a similar direction too, but focused on a plain REPL rather than notebook semantics or explicit session management beyond interrupts and restarts. It seems like the tradeoff is between keeping the interaction model simple and the context small, versus introducing notebook structure earlier and having the model work toward an artifact at the same time as it iterates and explores. Curious how you think about that balance?
Repo: https://github.com/posit-dev/mcp-repl
Thank you for this!
I am a big fan of Marimo and was trying to use it as my agent’s “REPL” a while back, because it’s naturally so good at describing its own current state and structure. It made me think that it would make a better state-preserving environment for the agent to work. I’m very excited to play with this.
One of the authors here, happy to answer questions.
Building pair has been a different kind of engineering for me. Code mode is not a versioned API. Its consumer is a model, not a program. The contract is between a runtime and something that reads docs and reasons about what it finds.
We've changed the surface several times without migrating the skill. The model picks up new instructions and discovers its capabilities within a session, and figures out the rest.
You could wrap pyobject via a proxy that controls context and have AI have a go at it. You can customise that interface however you want, have a stable interface that does things like ` proxy.describe() proxy.list_attrs() proxy.get_attr("columns") proxy.sample_rows(limit=5) proxy.children(path=["model", "layers"], limit=10) ` This way you get a general interface for AI interacting with your data, while still keeping a very fluid interface.
Built a custom kernel for notebooks with PDB and a similar interface, the trick is to also have access to the same API yourself (preferably with some extra views for humans), so you see the same mediated state the AI sees.
By 'wrap' I mean build a capability-based, effect-aware, versioned-object system on top of objects (execs and namespaces too) instead of giving models direct access. Not sure if your specific runtime constraints make this easier or harder. Does this sound like something you'd be moving towards?
How do you teach the model to use this new API? Wouldn't they be more effective just using the polars/pandas API which is has been well trained with?
Codex just picks it up. The surface is basically a guarded object model, so pandas/polars-style operations stay close to the APIs the model already knows. There's some extra-tricks but they're probably out of scope for an HN comment.
In practice, Pandas/Polars API would lower to: proxy -> attr("iloc") -> getitem(slice(1,10,None))
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.
https://github.com/madhavajay/cleon
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.