microsoftData & analytics

chartifact

Declarative, interactive data document format and runtime designed for LLM-generated reports and dashboards.

  • Web
  • IDE plugin
  • Library/framework
  • Browser
  • Windows
  • macOS
  • Linux
  • Self-hostable
  • Runs locally
  • Docker supported
chartifact screenshot
Popularity
80 Stars
GitHub stars
Recent activity
9/13/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Analytical conversations with AI lack a standard, secure format to generate shareable interactive documents.

Practical value

Includes reactive state, sandboxed rendering, Vega and Mermaid plugins, with VS Code preview and HTML export.

Innovation / differentiation

Blends Markdown and JSON blocks with reactive variables, enabling interactive UI state without custom JavaScript execution.

Leverage potential

Integrates across LLM workflows, VS Code tools, and web viewers, producing declarative files that language models can read and modify.

Why now

As language models are increasingly used for data analysis, secure and machine-readable document formats are needed.

Community activity

In the last 90 days there were 0 new issues and 33 pull requests; the bounded issue/PR samples include 0 issue authors and 2 PR contributors, with 0 releases.

Maintainer responsiveness

The 0-issue window sample had a — close rate, and the 33-pull-request sample had a 30% merge rate. Maintainer-comment observations covered only — of that issue sample, so response rate and first-response speed are not reported.

2 contributors in PR sample0 releasesPR merge rate 30% · 33 sampled in window

Key highlights

  • Declarative component schema for text, inputs, tables, Vega charts, and Mermaid diagrams.
  • Dual authoring formats supporting Markdown with JSON code blocks or standard JSON.
  • Reactive data flow keeping components and charts in sync via shared variables.

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

To be confirmed

Difficulty

To be confirmed

Docker supportedSelf-hostableRuns locally
  1. 01Access the official examples page to see sample documents.
  2. 02Install the Chartifact extension in VS Code.
  3. 03Create a Markdown file and define reactive variables and chart specifications in JSON blocks.
  4. 04Prompt an LLM to automatically generate the Chartifact document code.
  5. 05Preview and test the interactive functionality in the sandboxed preview window.
  6. 06Export the finished interactive document into a standalone HTML file.

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine
  • People who prefer Docker deploys

More about it

Chartifact is a low-code document format designed for creating interactive, data-driven reports, dashboards, and presentations. It combines the portability of standard documents with the rich interactivity of mini web applications, specifically designed to help LLMs produce shareable analytical artifacts. The project provides a unified document schema, a sandboxed execution runtime, a VS Code extension, and a web-based viewer. Authors can write in Markdown or JSON, leveraging Vega for data visualization, Mermaid for diagrams, and reactive variables to synchronize state across components securely.

Sources

Each field shows its status and source — expand to review.

14 · Expand
  • capability tags

    Verified

    Source: admin_cms · cms editor · 9/14/2026

  • editor note

    Verified

    {"en":"Chartifact combines human-readable Markdown with reactive state management and visualization engines like Vega and Mermaid. Its sandboxed architecture ensures secure rendering, making it ideal for LLM-generated interactive reports.","zh":"Chartifact 提供了清晰的数据响应式架构,将 Markdown 的易读性与 Vega、Mermaid 等图表渲染能力结合。其内置的沙盒运行机制保障了安全性,非常适合用于让大语言模型生成可交互的分析报告并导出为独立 HTML 文件。"}

    Source: admin_cms · cms editor · 9/14/2026

  • how to use

    Verified

    {"steps":[{"en":"Access the official examples page to see sample documents.","zh":"访问官方示例库查看已有数据文档展示。"},{"en":"Install the Chartifact extension in VS Code.","zh":"在 VS Code 编辑器中安装 Chartifact 插件。"},{"en":"Create a Markdown file and define reactive variables and chart specifications in JSON blocks.","zh":"创建 Markdown 文件,并在代码块中定义响应式变量与图表配置。"},{"en":"Prompt an LLM to automatically generate the Chartifact document code.","zh":"向大语言模型输入提示词,协助自动生成分析文档代码。"},{"en":"Preview and test the interactive functionality in the sandboxed preview window.","zh":"通过沙盒预览窗口实时查看和调试交互效果。"},{"en":"Export the finished interactive document into a standalone HTML file.","zh":"将制作完成的交互式文档导出为独立的 HTML 文件。"}],"installAt":"unknown","difficulty":"unknown"}

    Source: admin_cms · cms editor · 9/14/2026

  • intro

    Verified

    {"en":"Chartifact is a low-code document format designed for creating interactive, data-driven reports, dashboards, and presentations. It combines the portability of standard documents with the rich interactivity of mini web applications, specifically designed to help LLMs produce shareable analytical artifacts. The project provides a unified document schema, a sandboxed execution runtime, a VS Code extension, and a web-based viewer. Authors can write in Markdown or JSON, leveraging Vega for data visualization, Mermaid for diagrams, and reactive variables to synchronize state across components securely.","zh":"Chartifact 是一种声明式的低代码数据文档格式,用于创建可交互的数据报告、仪表盘和演示幻灯片。它兼具文档的便携性与轻量应用的交互能力,特别适合配合大语言模型将数据对话转化为可分享的分析成果。 该项目包含文档规范、沙盒运行时、VS Code 预览插件以及网页版查看器。使用者可以使用 Markdown 或 JSON 编写文档,利用 Vega 绘制数据图表、用 Mermaid 生成结构图,并通过响应式变量连接各类控件,快速构建出具备安全保障的动态数据网页。"}

    Source: admin_cms · cms editor · 9/14/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 9/14/2026

  • needs api key

    Verified

    No

    Source: admin_cms · cms editor · 9/14/2026

  • One-liner

    Verified

    {"en":"Declarative, interactive data document format and runtime designed for LLM-generated reports and dashboards.","zh":"声明式的交互式数据文档格式与运行时,适合配合大语言模型生成报表与仪表盘。"}

    Source: admin_cms · cms editor · 9/14/2026

  • Platforms

    Verified

    browser, windows, macos, linux

    Source: admin_cms · cms editor · 9/14/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/20/2026

  • product forms

    Verified

    web, ide_plugin, library_framework

    Source: admin_cms · cms editor · 9/14/2026

  • role tags

    Verified

    Source: admin_cms · cms editor · 9/14/2026

  • supports docker

    Verified

    Yes

    Source: Repository file · dockerfile=true; compose=true · 9/14/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

Other verified projects matched by category, capabilities, and intended roles.