Why Choose EdgeOne Makers for Sandbox Code Execution
Isolated code sandbox for AI agents — execute, modify, and preview code in secure environments with up to 3,600-second runtime per session.
One-Command Deployment
Deploy with `git push` for auto-deploy or `edgeone makers deploy` via CLI — no Docker, no Kubernetes, no server provisioning.
Built-in Agent Runtime
Managed runtime with session-sticky routing, up to 1-hour execution time, and in-memory state reuse — purpose-built for LLM calls and multi-step agent loops.
Integrated AI Models
Access DeepSeek, MiniMax, Hunyuan, and more through a unified AI gateway. New accounts receive 500K free tokens with zero configuration.
Full Observability
Zero-instrumentation distributed tracing — view complete call chains, LLM interactions, tool invocations, and latency metrics in local and cloud dashboards.
How to Run Sandbox Code on EdgeOne Makers
Deploy your agent and start running code sandbox tasks immediately — the platform provides isolated execution with zero configuration.
1
Write Your Agent
Build in the `agents/` directory with any framework (OpenAI SDK, Claude SDK, LangGraph, CrewAI, DeepAgents).
2
Deploy to Production
Push to Git (GitHub/GitLab/Gitee) for auto-deploy, or run `edgeone makers deploy` via CLI.
3
Go Live
Deploys globally in minutes with automatic SSL and edge routing.
Complete Sandbox Code Execution Features
Everything your AI agent needs for sandbox code execution — isolated runtime, file access, shell commands, and multi-language code sandbox support.
Feature | Description |
|---|---|
| Agent Runtime | Hosts LLM calls, Agent loop orchestration, and business logic, with session-based routing and automatic scaling. |
| Sandbox Tools | Provides two separate yet interoperable API layers for both LLMs and developers. Browser automation, code execution, Shell, and file operations all run in an isolated sandbox environment. |
| Conversation Storage | Provides framework-compatible memory management, with unified APIs for sessions and messages. |
| Observability | Automatically collects call traces with zero-intrusion instrumentation, enabling unified trace viewing in both local and cloud dashboards. |
| Built-in Models | Access Hunyuan and other mainstream Chinese models through AI Gateway with a limited-time free token quota. |
What is sandbox code execution on EdgeOne Makers?
Sandbox code execution lets your AI agent run code in an isolated environment. The code sandbox supports multiple languages, file I/O, and shell access — all within a secure per-session boundary.
How long can sandbox code run per session?
Each code sandbox instance supports up to 3,600 seconds (1 hour) of execution time, with a default timeout of 300 seconds. Suitable for complex coding tasks and iterative debugging.
Is sandbox code execution free?
Yes. Free tier provides 100,000 GB-s memory time for code sandbox usage, 20 concurrent instances, and up to 3,600-second runtime. No credit card required.
Can AI agents read and write files in the code sandbox?
Yes. The sandbox code environment includes full file system access — agents can create, read, modify, and delete files within the isolated code sandbox, enabling multi-file project generation and modification.
What languages does the code sandbox support?
The code sandbox supports multiple programming languages for execution. Agents can run JavaScript/TypeScript, Python, and shell scripts within the isolated sandbox code environment.