# marimo - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for marimo. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **AI researchers or builders of research-oriented Agents**: The README clearly centers on research, experiment, or paper workflows. Evidence: `README.md` Claim: `clm_0002` supported 0.86 - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0003` supported 0.86 ## What It Can Do - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md` Claim: `clm_0001` supported 0.86 ## How to Start - `pip install marimo && marimo tutorial intro` Evidence: `README.md` Claim: `clm_0004` supported 0.86 - `pip install marimo # or conda install -c conda-forge marimo` Evidence: `README.md` Claim: `clm_0005` supported 0.86 - `pip install "marimo[recommended]"` Evidence: `README.md` Claim: `clm_0006` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Trial role matching first - **Why**: This project is more of a role library; the core risk is picking the wrong role or treating role copy as execution capability. Trial role matching with Prompt Preview first, then decide whether to sandbox-import it. ### 30-Second Read - **What to do now**: Trial role matching first - **Minimum safe next step**: Trial role matching with Prompt Preview first; import in isolation only once satisfied - **Do not trust yet**: Role quality and task fit cannot be trusted directly. - **Continuing will touch**: Role selection bias, Command execution, Host AI configuration ### What You Can Trust Now - **Target-audience signal: AI researchers or builders of research-oriented Agents** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0002` supported 0.86 - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0003` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md` Claim: `clm_0001` supported 0.86 - **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0004` supported 0.86 ### What You Cannot Trust Yet - **Role quality and task fit cannot be trusted directly.** (unverified): A role library proves there are many roles; it does not prove each one fits your specific task or that a role produces high-quality results. - **Do not treat role copy as real execution capability.** (unverified): Before install you can only judge whether the role description and task profile match; you cannot prove it can complete the task inside the host AI. - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `AGENTS.md`, `CLAUDE.md` - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. ### What Continuing Will Touch - **Role selection bias**: The user's judgment about which expert role should handle the task. Why: Picking the wrong role makes the AI answer from the wrong expert perspective, wasting time or misleading decisions. - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md` - **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `AGENTS.md`, `CLAUDE.md` - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md` - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Use an interactive trial to verify the task profile and role match first; do not import the whole role library up front. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state. - **Keep a record of the original role selection**: If output goes off-topic, you can return to the task-profiling stage and reselect a role instead of pushing on with the wrong one. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0007` inferred 0.45 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md` Claim: `clm_0008` supported 0.86 - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md` Claim: `clm_0001` supported 0.86 ### Context Scale - Total files: 3474 - Important-file coverage: 40/3474 - Evidence index entries: 80 - Role / Skill entries: 72 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for marimo, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat marimo as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for marimo, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 72 role / Skill / project-doc entries. - **Documentation Apps** (project_doc): This directory contains marimo apps that are used in the documentation. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/apps/README.md` - **A reactive programming environment** (project_doc): A reactive Python notebook that's reproducible, git-friendly, and deployable as scripts or apps. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md` - **Docker Images** (project_doc): This directory contains the Dockerfile for building marimo Docker images. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docker/README.md` - **Examples** (project_doc): This folder contains example marimo notebooks, meant to teach you how to use marimo's features as well as inspire you to make awesome notebooks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/README.md` - **Readme** (project_doc): Development utilities. Should be run from the root directory of the project. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `scripts/README.md` - **Marimo notebook assistant** (project_doc): I am a specialized AI assistant designed to help create data science notebooks using marimo. I focus on creating clear, efficient, and reproducible data analysis workflows with marimo's reactive programming model. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/_static/CLAUDE.md` - **Agents** (project_doc): !!! warning "Experimental Feature" Agents are currently experimental and under active development. Features and APIs may change. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/guides/editor_features/agents.md` - **AI ๐Ÿค–** (project_doc): These examples showcase a few simple applications of AI. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/ai/README.md` - **Chat ๐Ÿ’ฌ** (project_doc): These examples show how to make chatbots with marimo, using mo.ui.chat https://docs.marimo.io/api/inputs/chat.html marimo.ui.chat . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/ai/chat/README.md` - **AI tool use ๐Ÿ› ** (project_doc): These are examples of using AI that interact with external functions and services. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/ai/tools/README.md` - **Cloud โ˜๏ธ** (project_doc): These examples show how to use various cloud provider APIs. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/cloud/README.md` - **Running marimo on Modal** (project_doc): This folder contains examples of how to run marimo notebooks on Modal https://modal.com/ , making it easy to get access to cloud GPUs. To get started, first create a modal account and follow their onboarding. You'll also need to install the uv package manager https://docs.astral.sh/uv/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/cloud/modal/README.md` - **Control Flow** (project_doc): These basic examples show how to control execution of cells. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/control_flow/README.md` - **Frameworks ๐Ÿงฉ** (project_doc): These examples show how to use marimo with various web/ASGI frameworks, such as FastAPI, Flask, and FastHTML. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/README.md` - **FastAPI + marimo: Authentication Middleware** (project_doc): FastAPI + marimo: Authentication Middleware Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/fastapi-auth/README.md` - **FastAPI + marimo, as an API endpoint** (project_doc): FastAPI + marimo, as an API endpoint Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/fastapi-endpoint/README.md` - **Server marimo notebooks from a GitHub repository** (project_doc): Server marimo notebooks from a GitHub repository Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/fastapi-github/README.md` - **FastAPI + marimo** (project_doc): This is a simple example of how to use FastAPI with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single FastAPI app. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/fastapi/README.md` - **FastHTML + marimo** (project_doc): This is a simple example of how to use FastHTML with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single FastHTML app. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/fasthtml/README.md` - **Flask + marimo** (project_doc): This is a simple example of how to use Flask with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single Flask app. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/frameworks/flask/README.md` - **Layouts ๐Ÿ“ฝ๏ธ** (project_doc): These examples show how to use marimo's built-in features for laying out notebooks in interesting ways, such as presenting notebooks as slides, adding sidebars, and arranging cells into columns while editing. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/layouts/README.md` - **Markdown** (project_doc): These basic examples show how to use write markdown in marimo. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/markdown/README.md` - **Misc โœจ** (project_doc): !TIP Submit a pull request https://github.com/marimo-team/marimo/pulls to add an example! Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/misc/README.md` - **SQL ๐Ÿ›ข๏ธ** (project_doc): These examples show how to use marimo's built-in support for SQL, which is powered by duckdb https://duckdb.org/ , a fast in-process analytical database. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sql/README.md` - **Misc. SQL examples ๐Ÿ›ข๏ธ** (project_doc): This folder contains illustrative examples of using SQL in marimo. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sql/misc/README.md` - **Third-party ๐Ÿ“ฆ** (project_doc): These examples showcase how to use various third-party packages in marimo. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/third_party/README.md` - **HuggingFace ๐Ÿ“ฆ** (project_doc): These examples showcase how to use HuggingFace's models in marimo. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/third_party/huggingface/README.md` - **Explore embeddings with MotherDuck** (project_doc): This notebook explores embeddings with MotherDuck's embeddings API. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/third_party/motherduck/embeddings/README.md` - **Sage: chat with any codebase ๐Ÿค–๐Ÿ’ฌ** (project_doc): This example shows how to create a notebook that lets you chat with any codebase , using Sage https://github.com/storia-ai/sage from Storia AI. It uses mo.ui.chat https://docs.marimo.io/api/inputs/chat.html with a custom chat function that implements a RAG-powered search over any GitHub repository of your choosing. The result is a chatbot that you can use to incrementally explore a codebase and even its associated Gโ€ฆ Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/third_party/sage/README.md` - **UI ๐Ÿ–ฑ๏ธ** (project_doc): These basic examples show how to use marimo's built-in UI elements. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/ui/README.md` - **E2E Tests** (project_doc): Rebuild the frontend for tests that take screenshots to view the latest changes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `frontend/e2e-tests/README.md` - **File Structure** (project_doc): Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `frontend/src/README.md` - **Charts** (project_doc): In order to maintain a consistent look and feel across all charts, we have a few components that are used to build the charts. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `frontend/src/components/data-table/charts/README.md` - **Schemas** (project_doc): This directory contains the schemas for the notebook, session, and kernel messages. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `marimo/_schemas/README.md` - **Process Isolation Smoke Test** (project_doc): Tests that multiple notebooks served together get separate OS processes, preventing sys.modules clashes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `marimo/_smoke_tests/process_isolation/README.md` - **Tutorial** (project_doc): This folder contains tutorials to help you get started with marimo. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `marimo/_tutorials/README.md` - **LLM Info** (project_doc): This package contains data for the LLM info. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `packages/llm-info/README.md` - **pytest-changed Plugin** (project_doc): A pytest plugin that uses ruff analyze graph to intelligently discover and run only the tests affected by code changes. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `packages/pytest_changed/README.md` - **@marimo-team/smart-cells** (project_doc): Parse "smart cells" markdown, SQL to-and-from Python code. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `packages/smart-cells/README.md` - **@marimo-team/tsconfig** (project_doc): Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `packages/ts-config/README.md` - **Testing ๐Ÿงช** (project_doc): These basic examples show how to use test marimo notebooks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/testing/README.md` - **marimo Development Guidelines** (project_doc): marimo is a reactive notebook for Python with a modern web frontend. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `AGENTS.md` - **Claude** (project_doc): Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CLAUDE.md` - **Frontend Guidelines** (project_doc): - Write clear, maintainable code over clever/short syntax - Use TypeScript with proper typing for all code - Use functional programming patterns; avoid classes - Favor composition over inheritance - Reduce code duplication, if you see code that is repeated, refactor it to a function or component. This standardizes the codebase. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `frontend/AGENTS.md` - **Python Backend Guidelines** (project_doc): Tests live in tests/ folder, mirroring marimo/ structure. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `marimo/AGENTS.md` - **Contributing Guide** (project_doc): We welcome contributions. You don't need to be an expert in frontend or Python development to help out. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CONTRIBUTING.md` - **marimo** (project_doc): Design system for marimo, a reactive Python notebook for reproducible, git-friendly, deployable work. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `DESIGN.md` - **Page Not Found** (project_doc): The page you're looking for doesn't exist. Find what you need in the marimo documentation. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/404.md` - **Cli** (project_doc): ::: mkdocs-click :module: marimo. cli.cli :command: main :prog name: marimo :depth: 0 :style: table Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/cli.md` - **Community** (project_doc): We're building a community. Come hang out with us! Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/community.md` - **Choosing marimo** (project_doc): Frequently asked questions about marimo: how it differs from Jupyter, why reactive execution, deployment, and troubleshooting. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/faq.md` - **marimo: The Reactive Python Notebook** (project_doc): marimo is an open-source reactive Python notebook. Run a cell or interact with a UI element, and marimo automatically runs dependent cells, keeping code and outputs consistent. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/index.md` - **Resources** (project_doc): marimo is a reinvention of the Python notebook. As a reinvention, marimo may push to you rethink what a notebook is . The following readings and videos might help you do just that. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/reading.md` - **Recipes** (project_doc): Code snippets and recipes for common marimo tasks: control flow, layout, data handling, state management, and more. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/recipes.md` - **Security** (project_doc): marimo takes security seriously. This document describes marimo's security model, our approach to vulnerability disclosure, and how to report security issues. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/security.md` - **App** (project_doc): ::: marimo.App options: members: - embed - run Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/app.md` - **Caching** (project_doc): marimo comes with utilities to cache intermediate computations. These utilities can be applied as decorators to functions to cache their returned values; you can choose between saving caches in memory or to disk. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/caching.md` - **Cell** (project_doc): Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/cell.md` - **Command Line Arguments** (project_doc): When running as a script with python notebook.py , command-line arguments are available to your program in sys.argv , just like any other Python program. This means you can use argparse https://docs.python.org/3/library/argparse.html , simple-parsing https://github.com/lebrice/SimpleParsing , and other tools for specifying and parsing arguments. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/cli_args.md` - **Control flow** (project_doc): Use mo.stop marimo.stop to halt execution of a cell when a condition is met. Combine mo.stop marimo.stop with mo.ui.run button marimo.ui.run button to gate execution on button click. Use mo.ui.refresh marimo.ui.refresh to make cells run periodically. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/control_flow.md` - **Diagrams** (project_doc): Customize Mermaid styling with theme and theme variables : Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/diagrams.md` - **HTML** (project_doc): All marimo elements extend the HTML element class. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/html.md` - **API Reference** (project_doc): Complete API reference for the marimo Python library: interactive inputs, markdown, layouts, media, control flow, and more. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/index.md` - **Building custom UI elements** (project_doc): Build custom UI plugins that hook into marimo's reactive execution engine by using anywidget https://anywidget.dev/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/anywidget.md` - **Array** (project_doc): python @app.cell def : wish = mo.ui.text placeholder="Wish" wishes = mo.ui.array wish 3, label="Three wishes" return Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/array.md` - **Batch** (project_doc): python @app.cell def : el = mo.md "{start} โ†’ {end}" .batch start=mo.ui.date label="Start Date" , end=mo.ui.date label="End Date" el return Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/batch.md` - **Button** (project_doc): !!! tip "Looking for a submit/run button?" If you're looking for a button to trigger computation on click, consider using mo.ui.run button marimo.ui.run button . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/button.md` - **Chat** (project_doc): !!! tip "Looking for example notebooks?" For example notebooks, check out examples/ai/chat on our GitHub https://github.com/marimo-team/marimo/tree/main/examples/ai/chat . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/chat.md` - **Checkbox** (project_doc): python @app.cell def : checkbox = mo.ui.checkbox label="check me" return Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/checkbox.md` - **Code Editor** (project_doc): /// marimo-embed-file filepath: examples/ui/code editor.py /// Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/code_editor.md` - **Data editor** (project_doc): /// marimo-embed-file size: xlarge filepath: examples/ui/data editor.py /// Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/data_editor.md` - **Data Explorer** (project_doc): The data explorer UI element outputs a visual editor explore your data via plotting and intelligent recommendations. You can incrementally build your "main" plot by adding different encodings: x-axis, y-axis, color, size, and shape. As you build your plot, the UI element will suggest further plots by intelligently "exploding" an additional encoding derived from your base plot. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/api/inputs/data_explorer.md` ## Evidence Index - Indexed 80 evidence entries. - **Documentation Apps** (documentation): This directory contains marimo apps that are used in the documentation. Evidence: `docs/apps/README.md` - **A reactive programming environment** (documentation): A reactive Python notebook that's reproducible, git-friendly, and deployable as scripts or apps. Evidence: `README.md` - **Docker Images** (documentation): This directory contains the Dockerfile for building marimo Docker images. Evidence: `docker/README.md` - **Examples** (documentation): This folder contains example marimo notebooks, meant to teach you how to use marimo's features as well as inspire you to make awesome notebooks. Evidence: `examples/README.md` - **Readme** (documentation): Development utilities. Should be run from the root directory of the project. Evidence: `scripts/README.md` - **Marimo notebook assistant** (documentation): I am a specialized AI assistant designed to help create data science notebooks using marimo. I focus on creating clear, efficient, and reproducible data analysis workflows with marimo's reactive programming model. Evidence: `docs/_static/CLAUDE.md` - **Agents** (documentation): !!! warning "Experimental Feature" Agents are currently experimental and under active development. Features and APIs may change. Evidence: `docs/guides/editor_features/agents.md` - **AI ๐Ÿค–** (documentation): These examples showcase a few simple applications of AI. Evidence: `examples/ai/README.md` - **Chat ๐Ÿ’ฌ** (documentation): These examples show how to make chatbots with marimo, using mo.ui.chat https://docs.marimo.io/api/inputs/chat.html marimo.ui.chat . Evidence: `examples/ai/chat/README.md` - **AI tool use ๐Ÿ› ** (documentation): These are examples of using AI that interact with external functions and services. Evidence: `examples/ai/tools/README.md` - **Cloud โ˜๏ธ** (documentation): These examples show how to use various cloud provider APIs. Evidence: `examples/cloud/README.md` - **Running marimo on Modal** (documentation): This folder contains examples of how to run marimo notebooks on Modal https://modal.com/ , making it easy to get access to cloud GPUs. To get started, first create a modal account and follow their onboarding. You'll also need to install the uv package manager https://docs.astral.sh/uv/ . Evidence: `examples/cloud/modal/README.md` - **Control Flow** (documentation): These basic examples show how to control execution of cells. Evidence: `examples/control_flow/README.md` - **Frameworks ๐Ÿงฉ** (documentation): These examples show how to use marimo with various web/ASGI frameworks, such as FastAPI, Flask, and FastHTML. Evidence: `examples/frameworks/README.md` - **FastAPI + marimo: Authentication Middleware** (documentation): FastAPI + marimo: Authentication Middleware Evidence: `examples/frameworks/fastapi-auth/README.md` - **FastAPI + marimo, as an API endpoint** (documentation): FastAPI + marimo, as an API endpoint Evidence: `examples/frameworks/fastapi-endpoint/README.md` - **Server marimo notebooks from a GitHub repository** (documentation): Server marimo notebooks from a GitHub repository Evidence: `examples/frameworks/fastapi-github/README.md` - **FastAPI + marimo** (documentation): This is a simple example of how to use FastAPI with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single FastAPI app. Evidence: `examples/frameworks/fastapi/README.md` - **FastHTML + marimo** (documentation): This is a simple example of how to use FastHTML with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single FastHTML app. Evidence: `examples/frameworks/fasthtml/README.md` - **Flask + marimo** (documentation): This is a simple example of how to use Flask with marimo. This example programmatically creates multiple marimo apps from a directory, and then serves them as a single Flask app. Evidence: `examples/frameworks/flask/README.md` - **Layouts ๐Ÿ“ฝ๏ธ** (documentation): These examples show how to use marimo's built-in features for laying out notebooks in interesting ways, such as presenting notebooks as slides, adding sidebars, and arranging cells into columns while editing. Evidence: `examples/layouts/README.md` - **Markdown** (documentation): These basic examples show how to use write markdown in marimo. Evidence: `examples/markdown/README.md` - **Misc โœจ** (documentation): !TIP Submit a pull request https://github.com/marimo-team/marimo/pulls to add an example! Evidence: `examples/misc/README.md` - **SQL ๐Ÿ›ข๏ธ** (documentation): These examples show how to use marimo's built-in support for SQL, which is powered by duckdb https://duckdb.org/ , a fast in-process analytical database. Evidence: `examples/sql/README.md` - **Misc. SQL examples ๐Ÿ›ข๏ธ** (documentation): This folder contains illustrative examples of using SQL in marimo. Evidence: `examples/sql/misc/README.md` - **Third-party ๐Ÿ“ฆ** (documentation): These examples showcase how to use various third-party packages in marimo. Evidence: `examples/third_party/README.md` - **HuggingFace ๐Ÿ“ฆ** (documentation): These examples showcase how to use HuggingFace's models in marimo. Evidence: `examples/third_party/huggingface/README.md` - **Explore embeddings with MotherDuck** (documentation): This notebook explores embeddings with MotherDuck's embeddings API. Evidence: `examples/third_party/motherduck/embeddings/README.md` - **Sage: chat with any codebase ๐Ÿค–๐Ÿ’ฌ** (documentation): This example shows how to create a notebook that lets you chat with any codebase , using Sage https://github.com/storia-ai/sage from Storia AI. It uses mo.ui.chat https://docs.marimo.io/api/inputs/chat.html with a custom chat function that implements a RAG-powered search over any GitHub repository of your choosing. The result is a chatbot that you can use to incrementally explore a codebase and even its associated GitHub issues. Evidence: `examples/third_party/sage/README.md` - **UI ๐Ÿ–ฑ๏ธ** (documentation): These basic examples show how to use marimo's built-in UI elements. Evidence: `examples/ui/README.md` - **E2E Tests** (documentation): Rebuild the frontend for tests that take screenshots to view the latest changes. Evidence: `frontend/e2e-tests/README.md` - **File Structure** (documentation): File Structure Evidence: `frontend/src/README.md` - **Charts** (documentation): In order to maintain a consistent look and feel across all charts, we have a few components that are used to build the charts. Evidence: `frontend/src/components/data-table/charts/README.md` - **Schemas** (documentation): This directory contains the schemas for the notebook, session, and kernel messages. Evidence: `marimo/_schemas/README.md` - **Process Isolation Smoke Test** (documentation): Tests that multiple notebooks served together get separate OS processes, preventing sys.modules clashes. Evidence: `marimo/_smoke_tests/process_isolation/README.md` - **Tutorial** (documentation): This folder contains tutorials to help you get started with marimo. Evidence: `marimo/_tutorials/README.md` - **LLM Info** (documentation): This package contains data for the LLM info. Evidence: `packages/llm-info/README.md` - **pytest-changed Plugin** (documentation): A pytest plugin that uses ruff analyze graph to intelligently discover and run only the tests affected by code changes. Evidence: `packages/pytest_changed/README.md` - **@marimo-team/smart-cells** (documentation): Parse "smart cells" markdown, SQL to-and-from Python code. Evidence: `packages/smart-cells/README.md` - **@marimo-team/tsconfig** (documentation): @marimo-team/tsconfig Shared tsconfig.json s. Evidence: `packages/ts-config/README.md` - **Testing ๐Ÿงช** (documentation): These basic examples show how to use test marimo notebooks. Evidence: `examples/testing/README.md` - **marimo Development Guidelines** (documentation): marimo is a reactive notebook for Python with a modern web frontend. Evidence: `AGENTS.md` - **Claude** (documentation): @AGENTS.md Evidence: `CLAUDE.md` - **Frontend Guidelines** (documentation): - Write clear, maintainable code over clever/short syntax - Use TypeScript with proper typing for all code - Use functional programming patterns; avoid classes - Favor composition over inheritance - Reduce code duplication, if you see code that is repeated, refactor it to a function or component. This standardizes the codebase. Evidence: `frontend/AGENTS.md` - **Python Backend Guidelines** (documentation): Tests live in tests/ folder, mirroring marimo/ structure. Evidence: `marimo/AGENTS.md` - **Package** (package_manifest): { "name": "@marimo-team/frontend", "version": "0.0.0-placeholder", "main": "dist/main.js", "types": "dist/index.d.ts", "type": "module", "license": "Apache-2.0", "repository": { "type": "git", "url": "https://github.com/marimo-team/marimo.git" }, "sideEffects": " .css", " .css.ts" , "files": "dist", "src" , "exports": { "./unstable internal/ ": "./src/ " }, "dependencies": { "@ai-sdk/react": "^3.0.134", "@anywidget/types": "^0.2.0", "@codemirror/autocomplete": "^6.20.1", "@codemirror/commands": "^6.10.2", "@codemirror/lang-markdown": "^6.5.0", "@codemirror/lang-python": "^6.2.1", "@codemirror/lang-sql": "^6.10.0", "@codemirror/language": "^6.12.2", "@codemirror/language-data": "^6.5.2", "@cโ€ฆ Evidence: `frontend/package.json` - **Package** (package_manifest): { "scripts": { "typecheck": "turbo typecheck", "format": "oxfmt --config .oxfmtrc.json", "test": "turbo test", "build": "turbo build", "codegen": "turbo run codegen", "lint": "pnpm run -r lint", "dev": "pnpm run --filter @marimo-team/frontend dev" }, "devDependencies": { "@testing-library/jest-dom": "^6.9.1", "@typescript/native-preview": "7.0.0-dev.20260324.1", "oxfmt": "^0.42.0", "turbo": "^2.8.0", "vitest": "^3.2.4" }, "engines": { "node": " =22", "pnpm": " =10.0.0" }, "packageManager": "pnpm@10.28.2" } Evidence: `package.json` - **Contributing Guide** (documentation): We welcome contributions. You don't need to be an expert in frontend or Python development to help out. Evidence: `CONTRIBUTING.md` - **Package** (package_manifest): { "name": "@marimo-team/llm-info", "version": "0.1.0", "private": true, "type": "module", "sideEffects": false, "files": "data/generated/ .json" , "exports": { ".": "./src/index.ts", "./icons/ ": "./icons/ ", "./models.json": "./data/generated/models.json", "./providers.json": "./data/generated/providers.json" }, "scripts": { "codegen": "node --experimental-transform-types src/generate.ts", "sync-models": "node --experimental-transform-types src/sync-models.ts", "test": "vitest", "build": "echo 'No build step'" }, "devDependencies": { "@marimo-team/tsconfig": "workspace: ", "yaml": "^2.8.2", "vitest": "^3.2.4", "zod": "^4.3.6" } } Evidence: `packages/llm-info/package.json` - **Package** (package_manifest): { "name": "@marimo-team/lsp", "main": "dist/index.cjs", "private": true, "license": "Apache-2.0", "scripts": { "build:ts": "tsup index.ts --format cjs --minify", "build:deps": "node move.js", "typecheck": "tsgo", "build": "pnpm run build:ts && pnpm run build:deps", "test": "vitest" }, "dependencies": { "@github/copilot-language-server": "^1.418.0" }, "devDependencies": { "@types/minimist": "^1.2.5", "@types/node": "^24.10.9", "@types/ws": "^8.18.1", "@vitest/expect": "^1.6.1", "jsonrpc-ws-proxy": "^0.0.5", "minimist": "^1.2.8", "tsup": "^8.5.1", "typescript": "^5.9.3", "vitest": "^3.2.4", "vscode-ws-jsonrpc": "^3.5.0", "ws": "^8.19.0" }, "packageManager": "pnpm@10.28.2" } Evidence: `packages/lsp/package.json` - **Package** (package_manifest): { "name": "@marimo-team/marimo-api", "version": "0.1.0", "private": true, "sideEffects": false, "main": "src/index.ts", "types": "src/index.ts", "type": "module", "license": "Apache-2.0", "files": "src" , "scripts": { "codegen": "pnpm run \"/^codegen:. /\" && npx oxfmt --config ../../.oxfmtrc.json src/", "codegen:api": "node ./convert types.js", "codegen:session": "openapi-typescript ../../marimo/ schemas/generated/session.yaml -o ./src/session.ts", "codegen:notebook": "openapi-typescript ../../marimo/ schemas/generated/notebook.yaml -o ./src/notebook.ts" }, "devDependencies": { "openapi-typescript": "^7.8.0", "typescript": "^5.9.3" }, "dependencies": { "openapi-fetch": "0.9.7" } } Evidence: `packages/openapi/package.json` - **Package** (package_manifest): { "name": "@marimo-team/smart-cells", "version": "0.1.0", "description": "Pure parsing library for marimo smart cells markdown, SQL, etc. ", "sideEffects": false, "main": "src/index.ts", "types": "src/index.ts", "type": "module", "files": "src" , "scripts": { "build": "echo 'No build step'", "test": "vitest", "typecheck": "tsgo" }, "dependencies": { "@codemirror/lang-python": "^6.2.1", "@lezer/common": "^1.5.1", "@lezer/python": "^1.1.18", "string-dedent": "^3.0.2" }, "devDependencies": { "@marimo-team/tsconfig": "workspace: ", "@types/node": "^20.19.30", "typescript": "^5.9.3", "vitest": "^3.2.4" }, "keywords": "marimo", "parser", "markdown", "sql", "python" , "license": "Apache-2.0" } Evidence: `packages/smart-cells/package.json` - **Package** (package_manifest): { "name": "@marimo-team/tsconfig", "version": "0.1.0", "private": true, "files": "base.json", "library.json", "ts-reset.d.ts" } Evidence: `packages/ts-config/package.json` - **License** (source_file): Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ Evidence: `LICENSE` - **Brand Assets** (documentation): - Logo SVG: https://raw.githubusercontent.com/marimo-team/marimo/main/docs/ static/marimo-logotype-thick.svg - Preserve the original aspect ratio. - Do not recolor unless explicitly requested. Evidence: `DESIGN.md` - **Page Not Found** (documentation): The page you're looking for doesn't exist or has been moved. Evidence: `docs/404.md` - **Cli** (documentation): ::: mkdocs-click :module: marimo. cli.cli :command: main :prog name: marimo :depth: 0 :style: table Evidence: `docs/cli.md` - **Community** (documentation): We're building a community. Come hang out with us! Evidence: `docs/community.md` - **Choosing marimo** (documentation): How is marimo different from Jupyter? Evidence: `docs/faq.md` - **marimo: The Reactive Python Notebook** (documentation): .md-typeset h1 { position: absolute; width: 1px; height: 1px; padding: 0; margin: -1px; overflow: hidden; clip: rect 0, 0, 0, 0 ; white-space: nowrap; border: 0; } .md-content button { display: none; } Evidence: `docs/index.md` - The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `docs/apps/README.md`, `README.md`, `docker/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `docs/apps/README.md`, `README.md`, `docker/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **marimo Overview & System Architecture**: importance `high` - source_paths: README.md, DESIGN.md, marimo/__init__.py, marimo/_ast/app.py, marimo/_runtime/dataflow/graph.py - **Reactive Runtime, Dataflow & Cell Execution**: importance `high` - source_paths: marimo/_runtime/runtime.py, marimo/_runtime/runner/scheduler.py, marimo/_runtime/runner/cell_runner.py, marimo/_runtime/dataflow/graph.py, marimo/_runtime/dataflow/topology.py - **Frontend Editor, UI Plugins & CodeMirror Integration**: importance `high` - source_paths: frontend/src/core/MarimoApp.tsx, frontend/src/components/editor/Output.tsx, frontend/src/core/codemirror/cm.ts, frontend/src/core/codemirror/cells/extensions.ts, frontend/src/components/dependency-graph/dependency-graph.tsx - **AI Integration, MCP, Deployment & Extensibility**: importance `high` - source_paths: marimo/_ai/_tools/tools/cells.py, marimo/_ai/text_to_notebook.py, marimo/_mcp/server/main.py, marimo/_mcp/code_server/main.py, marimo/_lint/rules/runtime/branch_expression.py ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `72bda05d539f369f53e5c3b003c4034071b88b08` - inspected_files: `README.md`, `package.json`, `pnpm-lock.yaml`, `pyproject.toml`, `docs/404.md`, `docs/_static/CLAUDE.md`, `docs/_static/js/analytics.js`, `docs/_static/js/init_kapa_widget.js`, `docs/_static/js/math.js`, `docs/_static/js/page_actions.js`, `docs/api/app.md`, `docs/api/caching.md`, `docs/api/cell.md`, `docs/api/cli_args.md`, `docs/api/control_flow.md`, `docs/api/diagrams.md`, `docs/api/html.md`, `docs/api/index.md`, `docs/api/inputs/anywidget.md`, `docs/api/inputs/array.md` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/marimo-team/marimo - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.