openclaw

中文版 | English

English

Sandbox runtime for the OpenClaw open-source AI coding agent, providing agent gateway and runtime support.

Environment

This template comes preinstalled with the following tools and dependencies:

Installation

Install from a local path:

abx template install ./openclaw --registry-type local

Install from GitHub:

abx template install alibaba-agent-sandbox/awesome-templates//openclaw

Usage

Create a sandbox instance and pass in the API key:

abx create --template openclaw --env ANTHROPIC_API_KEY=sk-ant-xxx

OpenAI can also be used as the backend:

abx create --template openclaw --env OPENAI_API_KEY=sk-xxx

Launch OpenClaw inside the sandbox:

abx exec <sandbox-id> -- openclaw --help

Using the Python SDK:

from agent_sandbox import Sandbox

sandbox = Sandbox.create_sync(
    template="openclaw",
    env={"ANTHROPIC_API_KEY": "sk-ant-xxx"}
)

result = sandbox.commands.run("openclaw --version")
print(result.stdout)

Configuration

Environment Variables

Ports

Custom Configuration

To install extra dependencies on top of this template, run the following after the sandbox is created:

abx exec <sandbox-id> -- npm install -g <package-name>

Notes

• API key security: Never hardcode API keys into the template; always inject them via the --env option or environment variables.
• Multi-model support: OpenClaw supports multiple LLM backends such as Anthropic and OpenAI — configure the corresponding API key as needed.
• Gateway port: Listens on port 18789 by default; reachable through sandbox port mapping.
• Network access: The LLM provider API must be reachable — make sure the sandbox has outbound internet connectivity.

中文

OpenClaw 开源 AI 编程 Agent 的沙箱运行环境，提供 Agent 网关与运行时支持。

环境说明

本模板预装以下工具和依赖：

安装方式

从本地安装：

abx template install ./openclaw --registry-type local

从 GitHub 安装：

abx template install alibaba-agent-sandbox/awesome-templates//openclaw

使用示例

创建沙箱实例并传入 API Key：

abx create --template openclaw --env ANTHROPIC_API_KEY=sk-ant-xxx

也可以使用 OpenAI 作为后端：

abx create --template openclaw --env OPENAI_API_KEY=sk-xxx

在沙箱中启动 OpenClaw：

abx exec <sandbox-id> -- openclaw --help

使用 Python SDK：

from agent_sandbox import Sandbox

sandbox = Sandbox.create_sync(
    template="openclaw",
    env={"ANTHROPIC_API_KEY": "sk-ant-xxx"}
)

result = sandbox.commands.run("openclaw --version")
print(result.stdout)

配置说明

环境变量

端口说明

自定义配置

如需在模板基础上安装额外依赖，可在创建沙箱后执行：

abx exec <sandbox-id> -- npm install -g <package-name>

注意事项

• API Key 安全：请勿将 API Key 硬编码到模板中，始终通过 --env 参数或环境变量注入。
• 多模型支持：OpenClaw 支持 Anthropic 和 OpenAI 等多种 LLM 后端，按需配置对应的 API Key。
• Gateway 端口：默认监听 18789 端口，可通过沙箱端口映射访问。
• 网络访问：需要访问 LLM 提供商 API，确保沙箱具备外网连接能力。

Deploy and local e2e

Install and register this template:

abx template install alibaba-agent-sandbox/awesome-templates//openclaw

From this directory (build, push, and register):

abx deploy

From the repository root, with agent-sandbox-server and httpx installed:

python3 scripts/run_local_e2e.py

That starts python3 commands.py in this directory and runs e2e_test.py.