Build isolated code execution environments on Cloudflare Workers for AI-generated code, scripts, and build pipelines. Covers running commands, managing files, preserving interpreter state, exposing service previews, and cleaning up sandbox resources.
中文简介正在准备中。当前显示英语简介。
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
安装前可以查看交给 AI 代理的指令内容。
Build secure, isolated code execution environments on Cloudflare Workers.
npm install @cloudflare/sandbox
docker info # Must succeed - Docker required for local dev
Your knowledge of the Sandbox SDK may be outdated. Prefer retrieval over pre-training for any Sandbox SDK task.
When implementing features, fetch the relevant doc page or example first.
wrangler.jsonc (exact - do not modify structure):
{
"containers": [{
"class_name": "Sandbox",
"image": "./Dockerfile",
"instance_type": "lite",
"max_instances": 1
}],
"durable_objects": {
"bindings": [{ "class_name": "Sandbox", "name": "Sandbox" }]
},
"migrations": [{ "new_sqlite_classes": ["Sandbox"], "tag": "v1" }]
}
Worker entry - must re-export Sandbox class:
import { getSandbox } from '@cloudflare/sandbox';
export { Sandbox } from '@cloudflare/sandbox'; // Required export
| Task | Method |
|---|---|
| Get sandbox | getSandbox(env.Sandbox, 'user-123') |
| Run command | await sandbox.exec('python script.py') |
| Run code (interpreter) | await sandbox.runCode(code, { language: 'python' }) |
| Write file | await sandbox.writeFile('/workspace/app.py', content) |
| Read file | await sandbox.readFile('/workspace/app.py') |
| Create directory | await sandbox.mkdir('/workspace/src', { recursive: true }) |
| List files | await sandbox.listFiles('/workspace') |
| Expose port | await sandbox.exposePort(8080) |
| Destroy | await sandbox.destroy() |
const sandbox = getSandbox(env.Sandbox, 'user-123');
const result = await sandbox.exec('python --version');
// result: { stdout, stderr, exitCode, success }
Use runCode() for executing LLM-generated code with rich outputs:
const ctx = await sandbox.createCodeContext({ language: 'python' });
await sandbox.runCode('import pandas as pd; data = [1,2,3]', { context: ctx });
const result = await sandbox.runCode('sum(data)', { context: ctx });
// result.results[0].text = "6"
Languages: python, javascript, typescript
State persists within context. Create explicit contexts for production.
await sandbox.mkdir('/workspace/project', { recursive: true });
await sandbox.writeFile('/workspace/project/main.py', code);
const file = await sandbox.readFile('/workspace/project/main.py');
const files = await sandbox.listFiles('/workspace/project');
| Need | Use | Why |
|---|---|---|
| Shell commands, scripts | exec() | Direct control, streaming |
| LLM-generated code | runCode() | Rich outputs, state persistence |
| Build/test pipelines | exec() | Exit codes, stderr capture |
| Data analysis | runCode() | Charts, tables, pandas |
Base image (docker.io/cloudflare/sandbox:0.7.0) includes Python 3.11, Node.js 20, and common tools.
Add dependencies by extending the Dockerfile:
FROM docker.io/cloudflare/sandbox:0.7.0
# Python packages
RUN pip install requests beautifulsoup4
# Node packages (global)
RUN npm install -g typescript
# System packages
RUN apt-get update && apt-get install -y ffmpeg && rm -rf /var/lib/apt/lists/*
EXPOSE 8080 # Required for local dev port exposure
Keep images lean - affects cold start time.
Expose HTTP services running in sandboxes:
const { url } = await sandbox.exposePort(8080);
// Returns preview URL for the service
Production requirement: Preview URLs need a custom domain with wildcard DNS (*.yourdomain.com). The .workers.dev domain does not support preview URL subdomains.
See: https://developers.cloudflare.com/sandbox/guides/expose-services/
The SDK provides helpers for OpenAI Agents at @cloudflare/sandbox/openai:
import { Shell, Editor } from '@cloudflare/sandbox/openai';
See examples/openai-agents for complete integration pattern.
getSandbox() returns immediately - container starts lazily on first operationsleepAfter)destroy() to immediately free resourcessandboxId always returns same sandbox instanceCommandClient, FileClient) - use sandbox.* methodsexport { Sandbox }destroy() for temporary sandboxes还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Review charts, diagrams, and dashboards for accessibility, including color contrast, keyboard access, and text alternatives. Get specific guidance for preserving key findings in screen readers, static exports, and reduced-motion views.
中文简介正在准备中。当前显示英语简介。
Give a photo collection a consistent look using Adobe tools to adjust color, tone, presets, and optional crops. Review a before-and-after sample before processing the full set, then receive links to the edited images.
中文简介正在准备中。当前显示英语简介。
Visualize a logo, sketch, or design on products such as mugs, shirts, and business cards. Review a pilot image, generate a visually consistent set, and collect the results on a shareable Firefly Board.
中文简介正在准备中。当前显示英语简介。
Prepare images and videos for social platforms using Adobe tools. Create image crops that keep the subject in view, expand backgrounds when available, preview a full-set sample, and resize videos while preserving their aspect ratio.
中文简介正在准备中。当前显示英语简介。
Create flyers, social posts, business cards, and other visuals from Adobe Express templates. Choose a template, customize its text and background color, and receive a design link, with additional editing and export options depending on the available tools.
中文简介正在准备中。当前显示英语简介。
Turn an uploaded video into three highlight edits with Adobe Quick Cut. Choose a target length and style, then compare versions that feature different moments and download the ones you prefer.
中文简介正在准备中。当前显示英语简介。