DESIGN/设计资源·UI-KIT
BoardUI/boardui
给 AI 聊天界面用的 React 组件库，每个组件能单独装进 Next.js 项目。React design system for agentic interfaces.
怎么装：Install: claude mcp add boardui -- npx -y boardui@latest mcp
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+10.0%+10.0%
551 → 606 stars · 7 个快照551 → 606 stars · 7 snapshots
状态STATUS
持续活跃Active
质量 A-Quality A-
项目 2026 年 9 月创建，到 10 月初已有 606 个 star，说明刚发布就有人关注。
03 / 它能帮你做什么03 / What it helps you do
用自己的密钥跑起一个能聊天的应用
把现成组件装进自己的 Next.js 项目
把界面改成从右往左读
一次拿走全部组件源码
用 npx boardui add 只挑需要的组件
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ MCP 客户端配置，粘贴到对应的配置文件里即可。An MCP client config — paste it into the relevant config file.
两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
在现有 Next.js 项目里运行 npx boardui@latest add data-table 来安装单个组件。
05 / 限制与风险05 / Limits and risk
风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.这不等于安全that does not mean it is safe，只能说明文档里没写。 — only that the docs do not mention it.
静态扫描未发现明显风险，但不代表安全。
这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
依赖：Dependencies:@ai-sdk/anthropic, @ai-sdk/google, @ai-sdk/openai, @ai-sdk/react, @internationalized/date, @remixicon/react, @tanstack/react-table, ai, motion, next, react, react-aria-components
{
"agents": [
{
"agent": "cursor",
"evidence": "tree: .cursor/"
},
{
"agent": "claude-code",
"evidence": "install: claude CLI command"
},
{
"agent": "vscode",
"evidence": "readme: …ens and type scale. Setup for VS Code, Codex and the rest is at [bo…"
}
],
"apiKey": "b.com%2FBoardUI%2Fboardui&env=AI_API_KEY&envDescription=Your+model+provider+key%",
"docker": null,
"taxonomy": {
"scores": {
"design": 10,
"ai-tools": 1,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 2,
"productivity": 0
},
"primary": "design",
"secondary": "ui-kit"
},
"localRuntime": "any OpenAI-compatible server (Ollama, LM Studio, vLLM, LiteLLM, Together) se",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 6,
"media": 0,
"design": 11,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}