--- title: Marimo Pair - A Canvas for Agent + Developers Collaboration description: Marimo pair is a new agent skill that drops a coding agent directly inside a running marimo notebook kernel, giving it live access to in-memory state rather... canonical: https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Marimo Pair - A Canvas for Agent + Developers Collaboration | daily.dev og:description: Marimo pair is a new agent skill that drops a coding agent directly inside a running marimo notebook kernel, giving it live access to in-memory state rather... og:url: https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461 og:image: https://api.daily.dev/og/posts/6b8diT461.png og:image:alt: Marimo Pair - A Canvas for Agent + Developers Collaboration og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Marimo Pair - A Canvas for Agent + Developers Collaboration **[Planet Python](https://daily.dev/sources/planetpython)** · [@mkennedy](https://daily.dev/mkennedy) · 25 min read · 1 upvotes · 0 comments ## Summary Marimo pair is a new agent skill that drops a coding agent directly inside a running marimo notebook kernel, giving it live access to in-memory state rather than just files on disk. The agent gets a single 'run Python' tool to inspect variables, data frames, and cell outputs, and can create, edit, and run cells — turning the notebook into a shared canvas for human-agent collaboration. This solves a core problem with existing coding agents and notebooks: agents previously could only edit .ipynb files without seeing live state, often producing inconsistent results. Marimo's reactive, data-flow-aware execution model also ensures the notebook remains reproducible as the agent builds it cell by cell. The skill is distributed via npm or uv/deno, works with Claude Code, Codex, and OpenCode, and supports both hands-on exploratory and headless workflows. Remote kernels are supported via marimo's cloud service molab on CoreWeave GPUs. The strategic design avoids competing with popular agents and instead makes marimo an excellent tool any agent can drive. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [GitHub - marimo-team/marimo-pair: Drop agents inside running marimo notebook sessions](https://daily.dev/posts/github---marimo-team-marimo-pair-drop-agents-inside-running-marimo-notebook-sessions-fvstbjvy4) · Hacker News · 3 upvotes · 0 comments - [Episode \#293: Agentic Data Science Pair Programming With marimo pair – The Real Python Podcast](https://daily.dev/posts/episode-293-agentic-data-science-pair-programming-with-marimo-pair-the-real-python-podcast-3zgeozdkk) · Real Python · 0 upvotes · 0 comments - [Announcing the marimo plugin for PyCharm](https://daily.dev/posts/announcing-the-marimo-plugin-for-pycharm-gdfhp1vla) · Hacker News · 0 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#ai-agents](https://daily.dev/tags/ai-agents), [#jupyter](https://daily.dev/tags/jupyter), [#exploratory-data-analysis](https://daily.dev/tags/exploratory-data-analysis) [View this post on daily.dev](https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Marimo Pair - A Canvas for Agent + Developers Collaboration","url":"https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461"},"datePublished":"2026-07-13T19:48:17.647Z","dateModified":"2026-08-24T07:00:28.682Z","description":"Marimo pair is a new agent skill that drops a coding agent directly inside a running marimo notebook kernel, giving it live access to in-memory state rather...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c167335a800f5a4b58ce87b65412f589?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c167335a800f5a4b58ce87b65412f589?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Planet Python","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Person","name":"Michael Kennedy","url":"https://daily.dev/mkennedy","image":"https://media.daily.dev/image/upload/s--CAIUuwxP--/f_auto,q_auto/v1701901463/avatars/avatar_5Q1yteeM08cxesQG2actL","description":"Python enthusiast. Host of @talkpython and @pythonbytes podcasts, founder of Talk Python Training.","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":30}},"commentCount":0,"discussionUrl":"https://daily.dev/posts/marimo-pair---a-canvas-for-agent-developers-collaboration-6b8dit461","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,ai-agents,jupyter,exploratory-data-analysis","timeRequired":"PT25M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Planet Python","item":"https://daily.dev/sources/planetpython"},{"@type":"ListItem","position":3,"name":"Marimo Pair - A Canvas for Agent + Developers Collaboration"}]} ```