• Product Introduction
  • Quick Start
    • Agent Development
    • Importing a Git Repository
    • Starting From a Template
    • Direct Upload
    • Start with AI
  • Framework Guide
    • Agent
    • Frontends
      • Vite
      • React
      • Vue
      • Hugo
      • Other Frameworks
    • Backends
    • Full-stack
      • Next.js
      • Nuxt
      • Astro
      • React Router
      • SvelteKit
      • TanStack Start
      • Vike
    • Custom 404 Page
  • Project Guide
    • Project Management
    • edgeone.json
    • Configuring Cache
    • Building Output Configuration
    • Domain Management
      • Overview
      • Custom Domain
      • HTTPS Configuration
        • Overview
        • Apply for Free Certificate
        • Using Managed SSL Certificate
      • Configure DNS CNAME Record
    • Error Codes
  • Build Guide
  • Deployment Guide
    • Overview
    • Create Deploys
    • Manage Deploys
    • Deploy Button
    • Using Github Actions
    • Using Gitlab CI/CD
    • Using CNB Plugin
    • Using IDE PlugIn
    • Using CodeBuddy IDE
  • Makers for Platforms
    • Platform and Multi-Tenancy
    • Vibe Coding Solution
    • Template Example
      • Vibe Coding General Template
      • Vibe Coding Platform Template
  • Observability
    • Overview
    • Metric Analysis
    • Log Analysis
  • Functions
    • Overview
    • Edge Functions
    • Cloud Functions
      • Overview
      • Node.js
      • Python
      • Go
  • Agents
    • Overview
    • Quick Start
    • Conversation Management
    • Observability
    • Sandbox Tool
      • Overview
      • Using the Agent Framework
      • Sandbox Atomic API
      • Network Search Tool
    • Agent Authentication
  • Models
    • Overview
    • Models and Vendors
      • Overview
      • Using the Zhuque Model
      • Using the Jev Model
      • Using Vendor Keys
        • OpenAI
        • Anthropic
        • Google AI Studio
        • DeepSeek
        • MiniMax
        • Hunyuan
        • Zhipu
        • MoonShot AI
    • FAQs
  • Storage
    • Overview
    • KV
    • Blob
  • Middleware
  • AI-Native Development
    • Skills
    • MCP
    • Plugin
  • Copilot
    • Overview
    • Quick Start
  • API Token
  • EdgeOne CLI
  • Makers SDK
    • Overview
    • Examples
      • Creating a Deployment
      • Deploying via the CLI
      • Project Management
    • Projects
      • Project Operations
      • Environment Variable
    • Deployment
  • Message Notification
  • Integration Guide
    • AI
      • Makers Models Integration
      • Large Models for Images Integration
    • Database
      • Supabase Integration
      • Pages KV Integration
    • Ecommerce
      • Shopify Integration
      • WooCommerce Integration
    • Payment
      • Stripe Integration
      • Integrating Paddle
    • CMS
      • WordPress Integration
      • Contentful Integration
      • Sanity Integration
      • Payload Integration
    • Authentication
      • Supabase Integration
      • Clerk Integration
    • IM
      • Overview
      • WeCom
      • Feishu
      • DingTalk
      • Telegram
      • slack
      • Discord
  • Best Practices
    • Adding an AI Chat Assistant to a Website
    • AI Dialogue Deployment: Deploy Project with One Sentence Using Skill
    • Building Agent Applications Quickly with Makers Agents
    • Building an Ecommerce Platform with Shopify
    • Building a SaaS Site Using Supabase and Stripe
    • Building a Company Brand Site Quickly
    • How to Quickly Build a Blog Site
    • Quick Launch via Login-Free Deployment in WorkBuddy
  • Migration Guides
    • Migrating from Vercel to EdgeOne Makers
    • Migrating from Cloudflare Pages to EdgeOne Makers
    • Migrating from Netlify to EdgeOne Makers
  • Troubleshooting
  • FAQs
  • Limits
  • Pricing
  • Contact Us
  • Release Notes

Vibe Coding Platform Template

The Vibe Coding Platform Template deeply integrates platform SKills capabilities and is suitable for rapidly generating full-stack Web applications and AI Agents based on Makers capabilities. Developers can use this template to quickly build a Vibe Coding platform that supports multi-tenant isolation, multi-framework adaptation, and one-click edge deployment.

Overall Architecture



Quick Start

1. Create and obtain an API Token.
2. Use the sample template below to quickly try it out and deploy with one click.

3. On the deployment configuration page, enter the API_TOKEN environment variable.
4. Click Deploy and wait for Makers to complete the build and generate an access URL.

Core Template Capabilities

Makers Skills Integration

The template has Makers Skills built in at .claude/skills/, providing the Agent with framework conventions, platform APIs, directory specifications, and deployment requirements.
The Agent uses the corresponding Skill based on the task. The generated project must first pass the Makers compatibility check, which verifies whether the framework adapter is in place, whether the platform declaration files are complete, and whether the directory structure is compliant. If the check fails, the Agent automatically attempts one round of repair.
You can update the platform's latest Skills by running npm run sync:skills, which will replace the .claude/skills/ directory.

Starting Preview

At runtime, the Agent constructs the command string for starting the preview, passes the tenant Token as a parameter, and then invokes the EdgeOne CLI through the sandbox's commands tool to start the project preview.

export function buildMakersDevLaunchCommand(port: number, projectName: string) {
return `edgeone makers dev -t ${token} --port ${port} --skip-env-sync --name ${shellQuote(projectName)}`;
}

Executing Deployment

At runtime, the Agent constructs the command string for deployment, passes the tenant Token as a parameter, and then invokes the EdgeOne CLI through the sandbox's commands tool to perform the deployment.

function makersDeployLaunch(projectName: string, requestedCommand: string, area = 'global') {
const previewEnvironment = /(?:^|\s)(?:-e|--environment)(?:\s+|=)preview(?:\s|$)/i
.test(requestedCommand);
return [
'edgeone makers deploy',
`-t ${token}`, // Tenant token
`-n ${shellQuote(projectName)}`,
'--json',
`--area ${area}`,
previewEnvironment ? '-e preview' : '',
].filter(Boolean).join(' ');
}
For the detailed deployment integration process, see Deploy through the CLI.

Code Persistence

Save workspace code
Call persist() after each round of code modifications:
try {
const persist = await context.sandbox.persist({path: projectPath}); // path is the project directory.
} catch (error) {
// A save failure does not prevent the current sandbox from continuing to work. You can log the error and retry later.
console.warn('Failed to save workspace:', error);
}
Restore workspace code
After a new sandbox is created, the Agent calls restore() before it starts reading from or writing to project files:
const result = await context.sandbox.restore({path: projectPath});
Note: If restore() returns failed, do not call persist() again in this round. Otherwise, you may overwrite the last available snapshot with an incomplete workspace.

Local Debugging and Deployment

Starting Local Development and Debugging

1. Go to the project root directory and install EdgeOne CLI:
npm install -g edgeone
2. Log in and associate the Makers project that was previously deployed using the template:
edgeone login
edgeone makers link
After the project is associated, the API_TOKEN configured in the console and the API Key required to call Models are automatically synchronized to the local environment.
3. Start the Makers local development environment:
edgeone makers dev
After a successful startup, visit http://localhost:8088/ to open the application. Visit http://localhost:8088/agent-metrics to view detailed trace information for Agent calls.

Deploying the Project

If the project is associated with a Git repository, pushing code triggers the CI build and deployment of Makers. You can also deploy directly through the CLI:
# Deploy to Production
edgeone makers deploy -n <project name>
After a successful deployment, click the link in the Console to access the build details and the deployed URL.
ai-agent