Vibe Coding Solution
Vibe Coding Agent enables end users to quickly create, modify, and publish applications through natural language, delivering a conversational app development experience similar to v0 and Lovable.
EdgeOne Makers integrates core capabilities such as production, deployment, compliance detection, access, and multi-tenant isolation into a single platform, enabling platform providers to build a complete Vibe Coding pipeline from conversational generation to real-time preview, application launch, and multi-tenant isolation without building or maintaining the underlying infrastructure.
Solution Value
Benefits | Specific Manifestation |
Integrated production environment | Agent orchestration, model invocation, session management, and sandbox tool access are closed-loop within the same runtime, reducing cross-service assembly and Ops workload. |
Isolation and lifecycle balance | Workspaces are isolated by session, while project code is retained through external persistence, balancing runtime security and continuous development experience. |
Unified cloud-edge delivery | Unified hosting of static, dynamic, full-stack, and Agent applications, with workloads running on the edge or in the cloud based on application form. |
Automatic project review | Provides project-level content security detection and risk handling capabilities, and notifies platform parties through event mechanisms when risks change. |
Overall Architecture
The production-side Coding Agent generates code by invoking large models and using sandbox tools. The deployment side publishes the generated applications to the Makers cloud-edge integrated runtime environment. The review side performs multi-layer compliance checks on live pages, deployment artifacts, and domains. The access side achieves low-latency access and security protection through edge access. Multi-tenant isolation ensures that each AI-generated project is deployed and runs independently.
Core Capabilities
Production Side: Coding Agent
It adopts a "separation of mind and hands" architecture, where the Agent runtime handles model invocation and business decisions, while the Sandbox handles file read/write operations, dependency installation, and code execution. Model, runtime, and sandbox capabilities are integrated into a unified solution, eliminating the need to assemble services across different platforms and enabling rapid construction of a Vibe Coding platform that supports continuous conversation, iteration, recovery, and full-chain tracing.
Agent Runtime
It handles LLM invocation, Agent loop orchestration, and business logic, and supports long-running tasks, session-based routing, and automatic scaling. It also supports Agent frameworks such as OpenAI and Claude, with native adaptation for session management and sandbox tool invocation capabilities.
Integrating Models
Makers Models provides a unified access channel from client SDKs to major model providers. Developers can invoke models from multiple mainstream providers through a unified endpoint and a single API Key, without needing to adapt to provider-specific interfaces or manage multiple sets of calling protocols.
Sandbox Tools
Sandbox tools use Tencent Cloud isolated instances under the hood to provide Agents with a secure and independent code execution environment, supporting command execution, file read/write operations, dependency installation, and code running. They also provide two independent yet interoperable API layers for LLMs and developers, eliminating the need to build or adapt execution environments separately.
Real-Time Preview
Preview is central to the Vibe Coding experience. Users need to see the result after code is generated. The preview address is mapped from a sandbox port and becomes invalid when the sandbox is reclaimed.
Code Persistence
A sandbox is a temporary workspace that is reclaimed upon timeout. To support users in resuming development across different time periods, project files must be persisted. Therefore, when you need to continue within the same session across different sandbox instances: call
persist() to save a snapshot, and after the instance is rebuilt, call restore() to restore it.
Deployment Side: Cloud-Edge Integration
Designed for Vibe Coding platforms, Makers provides a cloud-edge integrated production runtime environment for AI-generated multi-form applications, uniformly hosting static applications, full-stack applications, dynamic services, and Agent applications. Workloads are run on the edge or in the cloud based on the application form, achieving a balance between performance and elasticity.
Compliance Side: Automatic Project Review
For the domestic market, Vibe Coding platforms must address compliance challenges such as unpredictable AI-generated content, policy-violating content, and phishing impersonation. Makers provides project-level content security detection and risk handling capabilities, completing reviews before works are made public and syncing review results and risk changes through Webhooks. It also supports platforms in performing re-review, recovery, banning, and deletion on a per-project basis, achieving a complete closed loop from release review to continuous governance.
Access Side: Edge Access and Security
After the project goes live, requests are routed to the nearest EdgeOne global edge nodes (3,200+) for access, enabling both access acceleration and security protection to take effect simultaneously.
Multi-Tenant Isolation: Multiple Projects per Tenant
Each website corresponds to an independent project and automatically obtains an independent runtime environment. Tenants are isolated from each other and do not affect one another.
Open Source Project Examples
The Vibe Coding Universal Template is built on the Claude Agent SDK and TypeScript. It is suitable for generating Web applications that follow mainstream framework standards through natural language.
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.
