📄 工具详情 ⚙️ 安装教程 📚 使用教程

⚙️

Agent工作流

open-design — AI Agent 工作流中文教程

Q: open-design 如何安装和开始使用？

访问 open-design 的 GitHub 仓库或官方网站，按照 README 文档中的步骤安装依赖并运行。通常需要 Python 3.8+ 或 Node.js 16+ 基础环境。

Q: open-design 是否免费？许可证是什么？

open-design 完全免费，采用 Apache-2.0 许可证开源发布，任何人都可以免费使用、修改和分发。

Q: open-design 适合哪些用户使用？

open-design 主要面向有一定技术基础的用户，包括开发者、数据分析师、AI 工程师等专业人士。

Q: open-design 的社区活跃度和项目维护状况如何？

open-design 在 GitHub 上已获得 49,587 个 Star，是社区广泛认可的热门项目，持续活跃更新，维护良好。

基于 TypeScript · 无代码搭建完整 AI 自动化流程

英文名：open-design

⭐ 49.6k Stars 🍴 5.6k Forks 💻 TypeScript 📄 Apache-2.0 🏷 AI 9.8分

9.8AI 综合评分

agent-skillsai-agentsai-designbyokclaudeclaude-code-for-designclaude-skill

⬇ 下载源码 ZIP ⚙️ 配置说明

✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估，open-design — AI Agent 工作流中文教程获评「强烈推荐」。在 GitHub 上收获超过 49.6k 颗 Star，这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 9.8 分，适合有一定技术背景的用户使用。

📚 深度解析

open-design — AI Agent 工作流中文教程是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升，基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化（模拟鼠标键盘操作），AI Agent 工作流通过理解任务意图、动态规划执行路径，能够处理更复杂的非结构化任务。

open-design — AI Agent 工作流中文教程工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。

在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 9.8 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

open-design — AI Agent 工作流中文教程是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

GitHub Stars

⭐ 49.6k

开发语言

TypeScript

支持平台

Windows / macOS / Linux

维护状态

活跃维护，更新频繁

开源协议

Apache-2.0

AI 综合评分

9.8 分

工具类型

Agent工作流

Forks

5.6k

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

📌 核心特色

可视化 Agent 工作流编排，无需编写复杂代码
支持多步骤自动化任务链，实现全流程无人值守
与外部 API、数据库和第三方服务无缝集成
内置错误处理与自动重试机制，保障稳定运行
提供可复用的自动化模板，快速在同类场景部署

🎯 主要使用场景

自动化日常重复性工作，将精力集中于创造性任务
构建数据采集 → 处理 → 输出的完整自动化管线
实现跨平台、跨系统的数据流转和业务协同

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 方式一：npm 全局安装
npm install -g open-design

# 方式二：npx 直接运行（无需安装）
npx open-design --help

# 方式三：项目依赖安装
npm install open-design

# 方式四：从源码运行
git clone https://github.com/nexu-io/open-design
cd open-design
npm install
npm start

📋 安装步骤说明

访问 GitHub 仓库获取工作流文件
在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
上传工作流文件
按照提示配置必要的环境变量和 API Key
运行测试确认流程正常后投入使用

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 命令行使用
open-design --help

# 基本用法
open-design [options] <input>

# Node.js 代码中使用
const open_design = require('open-design');

const result = await open_design.run(options);
console.log(result);

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

# open-design 配置说明
# 查看配置选项
open-design --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量（覆盖配置文件）
export OPEN_DESIGN_CONFIG="/path/to/config.yml"

📑 README 深度解析真实文档完整度 50/100 查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

Download the desktop app (no build required)

The fastest way to try Open Design is the prebuilt desktop app — no Node, no pnpm, no clone:

open-design.ai — official download page
GitHub releases

Run with Docker

Run Open Design without installing Node.js or pnpm locally.

Requirements

Docker Desktop
Docker Compose v2

Verify Docker:

 id="70jv9o"
docker compose version

Start Open Design

 id="m9w43w"
git clone https://github.com/nexu-io/open-design.git
cd open-design/deploy
docker compose up -d

Open in your browser:

 id="4s4xeh"
http://localhost:7456

Common Commands

```bash id="gl95kp"

Showcase examples

The visually distinctive skills you'll most likely run first. Each ships a real example.html you can open straight from the repo to see exactly what the agent will produce — no auth, no setup.

_{dating-web · prototype Consumer dating / matchmaking dashboard — left rail nav, ticker bar, KPIs, 30-day mutual-matches chart, editorial typography.}	_{digital-eguide · template Two-spread digital e-guide — cover (title, author, TOC teaser) + lesson spread with pull-quote and step list. Creator / lifestyle tone.}
_{email-marketing · prototype Brand product-launch HTML email — masthead, hero image, headline lockup, CTA, specs grid. Centered single-column, table-fallback safe.}	_{gamified-app · prototype Three-frame gamified mobile-app prototype on a dark showcase stage — cover, today's quests with XP ribbons + level bar, quest detail.}
_{mobile-onboarding · prototype Three-frame mobile onboarding flow — splash, value-prop, sign-in. Status bar, swipe dots, primary CTA.}	_{motion-frames · prototype Single-frame motion-design hero with looping CSS animations — rotating type ring, animated globe, ticking timer. Hand-off ready for HyperFrames.}
_{social-carousel · prototype Three-card 1080×1080 social-media carousel — cinematic panels with display headlines that connect across the series, brand mark, loop affordance.}	_{sprite-animation · prototype Pixel / 8-bit animated explainer slide — full-bleed cream stage, animated pixel mascot, kinetic Japanese display type, looping CSS keyframes.}

Quickstart

2. Set REPO and APP_DATA to your actual paths; the example below is macOS + beta.

REPO="/path/to/open-design" APP_DATA="$HOME/Library/Application Support/Open Design/namespaces/release-beta/data"

2. Set $Repo and $AppData to your actual paths; the example below is stable channel.

$Repo = 'C:\path\to\open-design' $AppData = Join-Path $env:APPDATA 'Open Design\namespaces\release-stable-win\data'

Demo

_{Entry view — pick a skill, pick a design system, type the brief. The same surface for prototypes, decks, mobile apps, dashboards, and editorial pages.}	_{Turn-1 discovery form — before the model writes a pixel, OD locks the brief: surface, audience, tone, brand context, scale. 30 seconds of radios beats 30 minutes of redirects.}
_{Direction picker — when the user has no brand, the agent emits a second form with 5 curated directions (Monocle / Modern Minimal / Tech Utility / Brutalist / Soft Warm). One radio click → a deterministic palette + font stack, no model freestyle.}	_{Live todo progress — the agent's plan streams as a live card. in_progress → completed updates land in real time. The user can redirect cheaply, mid-flight.}
_{Sandboxed preview — every <artifact> renders in a clean srcdoc iframe. Editable in place via the file workspace; downloadable as HTML, PDF, ZIP.}	_{72-system library — every product system shows its 4-color signature. Click for the full DESIGN.md, swatch grid, and live showcase.}
_{Deck mode (guizang-ppt) — the bundled guizang-ppt-skill drops in unchanged. Magazine layouts, WebGL hero backgrounds, single-file HTML output, PDF export.}	_{Mobile prototype — pixel-accurate iPhone 15 Pro chrome (Dynamic Island, status bar SVGs, home indicator). Multi-screen prototypes use the shared /frames/ assets so the agent never re-draws a phone.}

Take a screenshot of the desktop app

pnpm tools-dev inspect desktop screenshot --path /tmp/open-design.png ```

The desktop app discovers the web URL automatically via sidecar IPC — no port guessing required.

gpt-image-2 — image gallery (sample of 43)

_{3D Stone Staircase Evolution Infographic
3-step infographic, hewn-stone aesthetic}

_{Illustrated City Food Map
Editorial hand-illustrated travel poster}

_{Cinematic Elevator Scene
Single-frame editorial fashion still}

2 · Skills are files, not plugins.

Following Claude Code's SKILL.md convention, each skill is SKILL.md + assets/ + references/. Drop a folder into skills/, restart the daemon, it appears in the picker. The bundled magazine-web-ppt is op7418/guizang-ppt-skill committed verbatim — original license preserved, attribution preserved.

then: imports = [ inputs.open-design.homeManagerModules.default ];

bash nix run github:nexu-io/open-design # boot the daemon (od) without installing


For developers, a Nix dev shell is available and can be used with `direnv` too:

bash nix develop # dev shell with required dependencies to work on Open Design ```

Open Design — the open-source Claude Design alternative

Open Design is the open-source, local-first alternative to [Claude Design][cd]. Web-deployable, BYOK at every layer — 16 coding-agent CLIs auto-detected on your PATH (Claude Code, Codex, Devin for Terminal, Cursor Agent, Gemini CLI, OpenCode, Qwen, Qoder CLI, GitHub Copilot CLI, Hermes, Kimi, Pi, Kiro, Kilo, Mistral Vibe, DeepSeek TUI) become the design engine, driven by 31 composable Skills and 72 brand-grade Design Systems. No CLI? An OpenAI-compatible BYOK proxy is the same loop minus the spawn.

[!IMPORTANT] ### 🔥 0.8.0-preview is here. Design's old world ends here. The open-source alternative to Claude Design / Figma — 40k stars in two weeks got us this far. We need you to push the rest of the way. Iterating fast on main — 0.8.0 is the next phase of Open Design. Ship a PR, drop a wild idea, file a bug — what you bring is what this movement becomes. → Read the announcement, grab the installer, join the movement · runs side-by-side with your current 0.7.

English · <a href="README.es.md">Español</a> · <a href="README.pt-BR.md">Português (Brasil)</a> · <a href="README.de.md">Deutsch</a> · <a href="README.fr.md">Français</a> · <a href="README.zh-CN.md">简体中文</a> · <a href="README.zh-TW.md">繁體中文</a> · <a href="README.ko.md">한국어</a> · <a href="README.ja-JP.md">日本語</a> · <a href="README.ar.md">العربية</a> · <a href="README.ru.md">Русский</a> · <a href="README.uk.md">Українська</a> · <a href="README.tr.md">Türkçe</a>

---

4 · The interactive question form prevents 80% of redirects.

OD's prompt stack hard-codes a RULE 1: every fresh design brief begins with a <question-form id="discovery"> instead of code. Surface · audience · tone · brand context · scale · constraints. A long brief still leaves design decisions open — visual tone, color stance, scale — exactly the things the form locks down in 30 seconds. The cost of a wrong direction is one chat round, not one finished deck.

This is the Junior-Designer mode distilled from huashu-design: batch the questions up front, show something visible early (even a wireframe with grey blocks), let the user redirect cheaply. Combined with the brand-asset protocol (locate · download · grep hex · write brand-spec.md · vocalise), it's the single biggest reason output stops feeling like AI freestyle and starts feeling like a designer who paid attention before painting.

📚 实用指南（长尾问题）

适合谁

需要让 Claude / Cursor 操作本地工具的 AI 工程师
构建多智能体协作系统的 Agent 开发者

最佳实践

配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
Agent 任务先做 dry-run 验证工具调用链，再开启自主执行

常见错误

API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
容器内无法访问宿主机 localhost — 使用 host.docker.internal
显存不足直接 OOM — 优先降低 context 或换更小的量化模型

部署方案

Docker：open-design 提供官方镜像，docker compose up 一键启动
CLI：直接 npm install -g / pip install，命令行调用
本地部署：CPU 8GB 起，GPU 推荐 16GB+ 显存
云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台

open-design — AI Agent 工作流中文教程

Download the desktop app (no build required)

Run with Docker

Requirements

Start Open Design

Common Commands

Showcase examples

Quickstart

2. Set REPO and APP_DATA to your actual paths; the example below is macOS + beta.

2. Set $Repo and $AppData to your actual paths; the example below is stable channel.

Demo

Take a screenshot of the desktop app

gpt-image-2 — image gallery (sample of 43)

2 · Skills are files, not plugins.

then: imports = [ inputs.open-design.homeManagerModules.default ];

Open Design — the open-source Claude Design alternative

4 · The interactive question form prevents 80% of redirects.

🤖 交给 Agent 安装 · open-design — AI Agent 工作流中文教程