Why Choose EdgeOne Makers for Claude Code Agent
The ideal claude code sandbox environment — isolated code execution, browser automation, shell access, and file I/O, all powered by claude code sdk on a managed platform.
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 Deploy a Claude Code Agent in 3 Steps
From claude code sdk project to production claude code agent with sandbox — deploy in minutes with zero infrastructure setup.
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 Claude Code Agent Features
Everything your claude code agent needs — isolated sandbox, code execution, browser, and shell access with claude code sdk on a managed runtime.
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 a claude code agent on EdgeOne Makers?
A claude code agent is an AI agent built with Claude SDK that can execute code, browse the web, run shell commands, and manipulate files in an isolated claude code sandbox environment.
What can the claude code sandbox do?
The claude code sandbox provides isolated browser automation, code execution (multiple languages), shell command access, and file system operations. All running in a secure, per-session environment.
Is hosting a claude code agent free?
Yes. Free tier: 200,000 executions/month, 100,000 GB-s sandbox memory time, 20 concurrent sandbox instances, and up to 3,600-second sandbox runtime.
Can I use my own Claude API key with the claude code agent?
Yes. While the platform provides built-in model access, you can bring your own Anthropic API key for Claude models. The claude code sdk works seamlessly with both platform-provided and custom keys.
Does the claude code agent support long-running tasks?
Yes. The agent runtime supports up to 1-hour execution, and the claude code sandbox supports up to 3,600 seconds — suitable for complex coding tasks, multi-file projects, and iterative debugging.