Blume：一个开源、零配置的文档框架，从 Markdown 文件夹生成 AI 就绪文档

Hayden Bleasel：https://haydenbleasel.com/，来自 OpenAI 的专家开发者，发布了 Blume：https://github.com/haydenbleasel/blume，这是一个开源文档框架。Blume 在同一天以 1.0.3 版本发布到 npm。使用非常简单，只需将 Markdown 文件放入文件夹即可生成文档网站。之后无需编写或维护应用程序模板。该项目采用 MIT 许可证开源。

Blume：https://github.com/haydenbleasel/blume 是一个命令行工具，与文档组件库配套使用。它读取一个包含 Markdown 或 MDX 文件的文件夹，并根据该文件夹生成一个生产级文档网站。生成的内容包括导航、搜索、主题和 Open Graph 图片。配置是可选的，可以一次添加一个文件。代码是 TypeScript monorepo；已发布的包位于 packages/blume。Blume 自身的文档位于 apps/docs，用 Blume 构建。它要求 Node.js 22.12 或更高版本。可用 Bun、pnpm、npm 或 yarn 运行。

在底层，Blume 会生成并运行一个隐藏的 Astro 项目。首先，CLI 加载 blume.config.ts 并将你的内容扫描成图结构。接着，它将一个 Astro 项目写入 .blume/ 目录。然后 Astro 通过单个 catch-all 路由渲染每个页面。该路由会导入 Blume 自带的组件、生成的数据以及你的覆盖内容。每次运行时，.blume/ 会重新生成，并且只重写更改的文件。因此，在编辑过程中热重载保持快速。核心主题不附带客户端框架 JavaScript。因此，页面默认在核心 Web 指标上得分良好。当你需要完全控制时，blume eject 可以将运行时升级为独立的 Astro 应用。升级后的项目仍依赖 blume 包。

设置只需一个命令，因此入门非常简短。

之后，blume dev 会启动热重载服务器。同时，blume build 会将静态 HTML 和本地搜索索引写入 dist/。配置文件是真正的 TypeScript，由模式验证。

由于配置是类型化的，编辑器可以在构建运行前捕获错误。CLI 涵盖了这些基本功能之外的完整生命周期：

除了面向人类读者，Blume 也面向智能代理。每个页面在 URL 后加上 .md 都会返回原始 Markdown。一个标志可以生成 llms.txt 和 llms-full.txt 供代理使用。每个页面可以作为 Markdown 复制或在 ChatGPT、Claude 或 v0 中打开。页面中可选的 Ask AI 助手可以直接回答读者问题。它通过 Vercel AI Gateway、OpenRouter、Inkeep 或任何兼容 OpenAI 的端点运行 AI SDK。Blume 还可以托管 Model Context Protocol (MCP) 服务器。通过它，Claude Code、Cursor 和 VS Code 可以直接读取文档。

该服务器提供四个只读工具：search_docs、get_page、list_pages 和 get_navigation。

这些功能对应具体任务。对于 API 产品，可上传 OpenAPI 或 AsyncAPI 规范。然后 Blume 会通过 Scalar 渲染包含模式、认证和请求演练 playground 的互动参考。对于库，指向你的 GitHub Releases。每个版本会汇总生成一个变更日志时间线，并提供 RSS 订阅。对于全球用户，可按区域添加翻译文件。Blume 支持 36 种语言、本地化路由和从右向左布局。对于混合内容，可以将本地文件与远程 MDX、Notion 或 Sanity 结合。所有来源通过相同组件渲染。

介绍 Blume —— 一个世界级的文档框架，适用于你发布的所有内容。将 Markdown 放入文件夹中，就可以无需应用模板发布完整文档网站。→ 零配置设置 → 自动 SEO 和 AEO → 30 个组件 → 由 astro + vite 提供支持 → 开源，永久免费 pic.twitter.com/fQSwLd9BM9：https://t.co/fQSwLd9BM9

为提供上下文，这里展示 Blume 与三种常见文档方案的对比。功能更新迅速，因此采纳前请核实当前情况。

需要与我们合作以推广你的 GitHub 仓库、Hugging Face 页面、产品发布或网络研讨会等？请联系： https://forms.gle/wbash1wF6efRj8G58

Hayden Bleasel：https://haydenbleasel.com/, an expert developer from OpenAI, released Blume：https://github.com/haydenbleasel/blume , an open-source documentation framework. Blume shipped to npm as version 1.0.3 the same day. It is as simple as Drop Markdown into a folder and ship a docs site. No app boilerplate is written or maintained afterward. The project is MIT-licensed and open sourced.

Blume：https://github.com/haydenbleasel/blume is a command-line tool paired with a component library for docs. It reads a folder of Markdown or MDX files. From that folder, it produces a production-grade documentation site. That output ships navigation, search, theming, and Open Graph images. Configuration stays optional and is added one file at a time. The code is a TypeScript monorepo; the published package sits at packages/blume . Blume’s own documentation, under apps/docs , is built with Blume itself. It requires Node.js 22.12 or newer. It runs with Bun, pnpm, npm, or yarn.

Under the surface, Blume generates and drives a hidden Astro project. First, the CLI loads blume.config.ts and scans your content into a graph. Next, it writes an Astro project into a .blume/ directory. Astro then renders every page through a single catch-all route. That route imports Blume’s shipped components, the generated data, and your overrides. On each run, .blume/ regenerates, and only changed files are rewritten. As a result, hot reload stays fast during editing. The core theme ships no client framework JavaScript. Consequently, pages score well on Core Web Vitals by default. When you need full control, blume eject promotes the runtime into a standalone Astro app. That ejected project still depends on the blume package.

Setup takes a single command, so onboarding is short.

Afterward, blume dev starts a hot-reloading server. Meanwhile, blume build writes static HTML and a local search index into dist/ . The config file is real TypeScript, validated by a schema.

Because the config is typed, editors catch mistakes before a build runs. The CLI covers the full lifecycle beyond those basics:

Beyond human readers, Blume targets agents too. Every page returns raw Markdown when you append .md to its URL. A single flag emits llms.txt and llms-full.txt for agents. Each page can be copied as Markdown or opened in ChatGPT, Claude, or v0. An optional in-page Ask AI assistant answers reader questions directly. It runs on the AI SDK through the Vercel AI Gateway, OpenRouter, Inkeep, or any OpenAI-compatible endpoint. Blume can also host a Model Context Protocol (MCP) server. Through it, Claude Code, Cursor, and VS Code read docs directly.

That server exposes four read-only tools: search_docs , get_page , list_pages , and get_navigation .

Those capabilities map to concrete jobs. For an API product, drop in an OpenAPI or AsyncAPI spec. Blume then renders an interactive reference with schemas, auth, and a request playground via Scalar. For a library, point Blume at your GitHub Releases. Each release rolls up into a generated changelog timeline with an RSS feed. For a global audience, add translated files per locale. Blume supports 36 locales, locale-aware routing, and right-to-left layouts. For mixed content, combine local files with remote MDX, Notion, or Sanity. All sources render through the same components.

Introducing Blume A world-class docs framework for everything you ship. Drop Markdown into a folder and ship a full docs site with no app boilerplate. → zero-config setup → automatic SEO and AEO → 30+ components → powered by astro + vite → open source, free forever pic.twitter.com/fQSwLd9BM9：https://t.co/fQSwLd9BM9

For context, here is Blume against three common documentation approaches. Features change quickly, so verify current details before you adopt.

Need to partner with us for promoting your GitHub Repo OR Hugging Face Page OR Product Release OR Webinar etc.? Connect with us ：https://forms.gle/wbash1wF6efRj8G58