Why Choose EdgeOne Makers AI Agent Sandbox
A complete ai sandbox with browser automation, code execution, shell, and file I/O — isolated per session, ready for any ai agent sandbox workload.
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 Use AI Agent Sandbox on EdgeOne Makers
Deploy your agent and get instant access to a fully isolated ai sandbox — no setup, no configuration, just deploy and use.
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 AI Agent Sandbox Features
Everything in the ai agent sandbox — browser, code runner, shell, file system, all isolated and secure for production ai sandbox workloads.
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 the AI agent sandbox on EdgeOne Makers?
The ai agent sandbox is an isolated execution environment providing browser automation, code execution, shell commands, and file system operations. Each sandbox instance is per-session and fully isolated from other users.
What tools are available in the ai sandbox?
The ai sandbox provides: browser automation (navigate, click, extract), code execution (multiple languages), shell command access, and file system read/write operations. All tools are available to both the LLM layer and developer layer.
Is the ai agent sandbox free?
Yes. Free tier includes 100,000 GB-s sandbox memory time, 20 concurrent sandbox instances, and up to 3,600-second runtime per instance. No credit card required.
How is the ai agent sandbox isolated?
Each ai sandbox instance runs in a per-session isolated environment. No data, processes, or network state is shared between different sessions or users, ensuring complete security for sensitive operations.
Can I use the sandbox as a no code ai development sandbox?
Yes. The ai agent sandbox provides pre-built tool primitives (browser, code, shell, files) that agents can invoke without writing additional infrastructure code — creating a no code ai development sandbox environment for rapid prototyping.