Sandbox Agent - AI 编码代理沙盒环境编排工具，支持多语言 SDK 和云服务集成

sandbox-agent by rivet-dev/skills

2,500 周安装量

8 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/rivet-dev/skills --skill sandbox-agent

AI/机器学习开发开发运维

🇨🇳中文介绍

Sandbox Agent

Sandbox Agent 提供了一个通用 API，用于在沙盒环境中编排 AI 编码代理。

遇到问题怎么办

如果某些功能未按预期工作或您遇到困难，请提示用户加入 Rivet Discord 或在 GitHub 上提交问题以报告问题并获取帮助。

向用户提供一份预生成的报告，内容包括：

症状
- 此问题是发生在本地开发环境、部署环境，还是两者都有
- 您看到的错误信息
- 与此相关的源代码
您已尝试的解决方法
环境信息
- Sandbox Agent 版本
- 使用的 SDK（TypeScript、Python 或 HTTP）
- 使用的代理（Claude Code、Codex、OpenCode、Amp、Mock）
- 沙盒提供商（E2B、Daytona、Docker、local）

快速开始

安装技能（可选）

npx

npx skills add rivet-dev/skills -s sandbox-agent

bunx

bunx skills add rivet-dev/skills -s sandbox-agent

设置环境变量

每个编码代理都需要 API 密钥来连接其对应的 LLM 提供商。

本地 Shell

export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

733,500 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

252,100 周安装

Vercel Web界面规范检查工具 - 自动检测代码是否符合Web设计指南

202,600 周安装

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

133,200 周安装

import { Sandbox } from "@e2b/code-interpreter";

const envs: Record<string, string> = {};
if (process.env.ANTHROPIC_API_KEY) envs.ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (process.env.OPENAI_API_KEY) envs.OPENAI_API_KEY = process.env.OPENAI_API_KEY;

const sandbox = await Sandbox.create({ envs });

import { Daytona } from "@daytonaio/sdk";

const envVars: Record<string, string> = {};
if (process.env.ANTHROPIC_API_KEY) envVars.ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (process.env.OPENAI_API_KEY) envVars.OPENAI_API_KEY = process.env.OPENAI_API_KEY;

const daytona = new Daytona();
const sandbox = await daytona.create({
  snapshot: "sandbox-agent-ready",
  envVars,
});

docker run -p 2468:2468 \
  -e ANTHROPIC_API_KEY="sk-ant-..." \
  -e OPENAI_API_KEY="sk-..." \
  rivetdev/sandbox-agent:0.5.0-rc.1-full \
  server --no-token --host 0.0.0.0 --port 2468

从当前机器提取 API 密钥

使用 sandbox-agent credentials extract-env --export 从本地的 Claude Code 或 Codex 配置文件中提取您现有的 API 密钥（Anthropic、OpenAI 等）。

无 API 密钥测试

使用 mock 代理进行 SDK 和集成测试，无需提供商凭据。

多租户和按用户计费

对于按租户令牌跟踪、预算强制执行或基于使用量的计费，请参阅 LLM Credentials 以了解 OpenRouter、LiteLLM 和 Portkey 等网关选项。

直接安装并运行二进制文件。

curl -fsSL https://releases.rivet.dev/sandbox-agent/0.3.x/install.sh | sh
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

无需全局安装即可运行。

npx @sandbox-agent/cli@0.3.x server --no-token --host 0.0.0.0 --port 2468

无需全局安装即可运行。

bunx @sandbox-agent/cli@0.3.x server --no-token --host 0.0.0.0 --port 2468

全局安装，然后运行。

npm install -g @sandbox-agent/cli@0.3.x
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

全局安装，然后运行。

bun add -g @sandbox-agent/cli@0.3.x
# 允许 Bun 为原生二进制文件运行 postinstall 脚本（SandboxAgent.start() 所需）。
bun pm -g trust @sandbox-agent/cli-linux-x64 @sandbox-agent/cli-linux-arm64 @sandbox-agent/cli-darwin-arm64 @sandbox-agent/cli-darwin-x64 @sandbox-agent/cli-win32-x64
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

对于本地开发，使用 SandboxAgent.start() 来生成和管理服务器作为子进程。

npm install sandbox-agent@0.3.x



import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.start();

对于本地开发，使用 SandboxAgent.start() 来生成和管理服务器作为子进程。

bun add sandbox-agent@0.3.x
# 允许 Bun 为原生二进制文件运行 postinstall 脚本（SandboxAgent.start() 所需）。
bun pm trust @sandbox-agent/cli-linux-x64 @sandbox-agent/cli-linux-arm64 @sandbox-agent/cli-darwin-arm64 @sandbox-agent/cli-darwin-x64 @sandbox-agent/cli-win32-x64



import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.start();

如果您是从源代码运行，而不是使用已安装的 CLI。

cargo run -p sandbox-agent -- server --no-token --host 0.0.0.0 --port 2468

绑定到 0.0.0.0 允许服务器接受来自任何网络接口的连接，这在客户端远程连接的沙盒内运行时是必需的。

通常不需要令牌。大多数沙盒提供商（E2B、Daytona 等）已经在基础设施层确保了网络安全。

如果您将服务器公开暴露，请使用 --token "$SANDBOX_TOKEN" 来要求身份验证：

sandbox-agent server --token "$SANDBOX_TOKEN" --host 0.0.0.0 --port 2468

然后在连接时传递令牌：

import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.connect({
  baseUrl: "http://your-server:2468",
  token: process.env.SANDBOX_TOKEN,
});

curl "http://your-server:2468/v1/health" \
  -H "Authorization: Bearer $SANDBOX_TOKEN"

sandbox-agent --token "$SANDBOX_TOKEN" api agents list \
  --endpoint http://your-server:2468

如果您从浏览器调用服务器，请参阅 CORS 配置指南。

安装代理（可选）

要预安装代理：

sandbox-agent install-agent --all

如果代理没有预先安装，它们会在创建会话时按需安装。

安装桌面依赖项（可选，仅限 Linux）

如果您想使用 /v1/desktop/*，请先安装桌面运行时包：

sandbox-agent install desktop --yes

然后在使用桌面截图或输入 API 之前，使用 GET /v1/desktop/status 或 sdk.getDesktopStatus() 来验证运行时是否准备就绪。

import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.connect({
  baseUrl: "http://127.0.0.1:2468",
});

const session = await sdk.createSession({
  agent: "claude",
  sessionInit: {
    cwd: "/",
    mcpServers: [],
  },
});

console.log(session.id);

const result = await session.prompt([
  { type: "text", text: "Summarize the repository and suggest next steps." },
]);

console.log(result.stopReason);

const off = session.onEvent((event) => {
  console.log(event.sender, event.payload);
});

const page = await sdk.getEvents({
  sessionId: session.id,
  limit: 50,
});

console.log(page.items.length);
off();

使用 Inspector 进行测试

在您的服务器上打开 /ui/ 的 Inspector UI（例如，http://localhost:2468/ui/），以便在 GUI 中检查会话和事件。

会话持久化 — 配置内存、Rivet Actor 状态、IndexedDB、SQLite 和 Postgres 持久化。
部署到沙盒 — 将您的代理部署到 E2B、Daytona、Docker、Vercel 或 Cloudflare。
SDK 概述 — 使用最新的 TypeScript SDK API。

🇺🇸English

Sandbox Agent

Sandbox Agent provides a universal API for orchestrating AI coding agents in sandboxed environments.

What To Do If You Get Stuck

If something is not working as intended or you are stuck, prompt the user to join the Rivet Discord or file an issue on GitHub to report an issue and get help.

Provide the user with a pre-generated report with:

Symptoms
- If this is happening in local dev, deployed, or both
- The error you're seeing
- Relevant source code related to this
What you've tried to solve it
Environment
- Sandbox Agent version
- SDK in use (TypeScript, Python, or HTTP)
- Agent in use (Claude Code, Codex, OpenCode, Amp, Mock)
- Sandbox provider (E2B, Daytona, Docker, local)

Quickstart

Install skill (optional)

npx

npx skills add rivet-dev/skills -s sandbox-agent

bunx

bunx skills add rivet-dev/skills -s sandbox-agent

Set environment variables

Each coding agent requires API keys to connect to their respective LLM providers.

Local shell

export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."

E2B

import { Sandbox } from "@e2b/code-interpreter";

const envs: Record<string, string> = {};
if (process.env.ANTHROPIC_API_KEY) envs.ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (process.env.OPENAI_API_KEY) envs.OPENAI_API_KEY = process.env.OPENAI_API_KEY;

const sandbox = await Sandbox.create({ envs });

Daytona

import { Daytona } from "@daytonaio/sdk";

const envVars: Record<string, string> = {};
if (process.env.ANTHROPIC_API_KEY) envVars.ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (process.env.OPENAI_API_KEY) envVars.OPENAI_API_KEY = process.env.OPENAI_API_KEY;

const daytona = new Daytona();
const sandbox = await daytona.create({
  snapshot: "sandbox-agent-ready",
  envVars,
});

Docker

docker run -p 2468:2468 \
  -e ANTHROPIC_API_KEY="sk-ant-..." \
  -e OPENAI_API_KEY="sk-..." \
  rivetdev/sandbox-agent:0.5.0-rc.1-full \
  server --no-token --host 0.0.0.0 --port 2468

Extracting API keys from current machine

Use sandbox-agent credentials extract-env --export to extract your existing API keys (Anthropic, OpenAI, etc.) from local Claude Code or Codex config files.

Testing without API keys

Use the mock agent for SDK and integration testing without provider credentials.

Multi-tenant and per-user billing

For per-tenant token tracking, budget enforcement, or usage-based billing, see LLM Credentials for gateway options like OpenRouter, LiteLLM, and Portkey.

Run the server

curl

Install and run the binary directly.

curl -fsSL https://releases.rivet.dev/sandbox-agent/0.3.x/install.sh | sh
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

npx

Run without installing globally.

npx @sandbox-agent/cli@0.3.x server --no-token --host 0.0.0.0 --port 2468

bunx

Run without installing globally.

bunx @sandbox-agent/cli@0.3.x server --no-token --host 0.0.0.0 --port 2468

npm i -g

Install globally, then run.

npm install -g @sandbox-agent/cli@0.3.x
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

bun add -g

Install globally, then run.

bun add -g @sandbox-agent/cli@0.3.x
# Allow Bun to run postinstall scripts for native binaries (required for SandboxAgent.start()).
bun pm -g trust @sandbox-agent/cli-linux-x64 @sandbox-agent/cli-linux-arm64 @sandbox-agent/cli-darwin-arm64 @sandbox-agent/cli-darwin-x64 @sandbox-agent/cli-win32-x64
sandbox-agent server --no-token --host 0.0.0.0 --port 2468

Node.js (local)

For local development, use SandboxAgent.start() to spawn and manage the server as a subprocess.

npm install sandbox-agent@0.3.x



import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.start();

Bun (local)

For local development, use SandboxAgent.start() to spawn and manage the server as a subprocess.

bun add sandbox-agent@0.3.x
# Allow Bun to run postinstall scripts for native binaries (required for SandboxAgent.start()).
bun pm trust @sandbox-agent/cli-linux-x64 @sandbox-agent/cli-linux-arm64 @sandbox-agent/cli-darwin-arm64 @sandbox-agent/cli-darwin-x64 @sandbox-agent/cli-win32-x64



import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.start();

Build from source

If you're running from source instead of the installed CLI.

cargo run -p sandbox-agent -- server --no-token --host 0.0.0.0 --port 2468

Binding to 0.0.0.0 allows the server to accept connections from any network interface, which is required when running inside a sandbox where clients connect remotely.

Configuring token

Tokens are usually not required. Most sandbox providers (E2B, Daytona, etc.) already secure networking at the infrastructure layer.

If you expose the server publicly, use --token "$SANDBOX_TOKEN" to require authentication:

sandbox-agent server --token "$SANDBOX_TOKEN" --host 0.0.0.0 --port 2468

Then pass the token when connecting:

TypeScript

import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.connect({
  baseUrl: "http://your-server:2468",
  token: process.env.SANDBOX_TOKEN,
});

curl

curl "http://your-server:2468/v1/health" \
  -H "Authorization: Bearer $SANDBOX_TOKEN"

CLI

sandbox-agent --token "$SANDBOX_TOKEN" api agents list \
  --endpoint http://your-server:2468

CORS

If you're calling the server from a browser, see the CORS configuration guide.

Install agents (optional)

To preinstall agents:

sandbox-agent install-agent --all

If agents are not installed up front, they are lazily installed when creating a session.

Install desktop dependencies (optional, Linux only)

If you want to use /v1/desktop/*, install the desktop runtime packages first:

sandbox-agent install desktop --yes

Then use GET /v1/desktop/status or sdk.getDesktopStatus() to verify the runtime is ready before calling desktop screenshot or input APIs.

Create a session

import { SandboxAgent } from "sandbox-agent";

const sdk = await SandboxAgent.connect({
  baseUrl: "http://127.0.0.1:2468",
});

const session = await sdk.createSession({
  agent: "claude",
  sessionInit: {
    cwd: "/",
    mcpServers: [],
  },
});

console.log(session.id);

Send a message

const result = await session.prompt([
  { type: "text", text: "Summarize the repository and suggest next steps." },
]);

console.log(result.stopReason);

Read events

const off = session.onEvent((event) => {
  console.log(event.sender, event.payload);
});

const page = await sdk.getEvents({
  sessionId: session.id,
  limit: 50,
});

console.log(page.items.length);
off();

Test with Inspector

Open the Inspector UI at /ui/ on your server (for example, http://localhost:2468/ui/) to inspect sessions and events in a GUI.

Sandbox Agent Inspector

Next steps

Session Persistence — Configure in-memory, Rivet Actor state, IndexedDB, SQLite, and Postgres persistence.
Deploy to a Sandbox — Deploy your agent to E2B, Daytona, Docker, Vercel, or Cloudflare.
SDK Overview — Use the latest TypeScript SDK API.

Reference Map

Agents

AI

Deploy

General

Weekly Installs

2.5K

Repository

rivet-dev/skills

GitHub Stars

First Seen

Jan 29, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykFail

Installed on

github-copilot2.4K

opencode1.6K

codex1.6K

gemini-cli1.5K

amp1.5K

kimi-cli1.5K

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

102,200 周安装

Sandbox Agent - AI 编码代理沙盒环境编排工具，支持多语言 SDK 和云服务集成

🇨🇳中文介绍

Sandbox Agent

遇到问题怎么办

快速开始

安装技能（可选）

npx

bunx

设置环境变量

本地 Shell

相关 Skills

E2B

Daytona

Docker

从当前机器提取 API 密钥

无 API 密钥测试

多租户和按用户计费

运行服务器

curl

npx

bunx

npm i -g

bun add -g

Node.js（本地）

Bun（本地）

从源代码构建

配置令牌

TypeScript

curl

CLI

CORS

安装代理（可选）

安装桌面依赖项（可选，仅限 Linux）

创建会话

发送消息

读取事件

使用 Inspector 进行测试

后续步骤

参考地图

代理

AI

部署

通用

🇺🇸English

Sandbox Agent

What To Do If You Get Stuck

Quickstart

Install skill (optional)

npx

bunx

Set environment variables

Local shell

E2B

Daytona

Docker

Extracting API keys from current machine

Testing without API keys

Multi-tenant and per-user billing

Run the server

curl

npx

bunx

npm i -g

bun add -g

Node.js (local)

Bun (local)

Build from source

Configuring token

TypeScript

curl

CLI

CORS

Install agents (optional)

Install desktop dependencies (optional, Linux only)

Create a session

Send a message

Read events

Test with Inspector

Next steps

Reference Map