본문으로 건너뛰기
cccskills
무료GitHub에 공개

e2b

E2B Desktop Sandbox with autonomous computer use — cloud Linux environments for browser automation, visual UI grounding, screenshot analysis, and shell execution. Supports Browser Use cloud sessions, Playwright integration, and LLM-driven desktop control. Use when asked about sandboxes, computer use, browser automation, E2B, desktop control, visual testing, or cloud Linux environments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구PlaywrightOpenAI
설치 방법 보기

포함된 파일(1)

  • SKILL.md10.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

E2B — Cloud Desktop Sandbox & Computer Use

Secure cloud Linux desktops powered by E2B Desktop Sandbox with autonomous computer-use capabilities, Browser Use integration, and LLM-driven visual control.

Quick Start

# Set up environment
export E2B_API_KEY="your-e2b-api-key"
export BROWSERUSE_API_KEY="your-browseruse-api-key"  # Optional: for cloud browser sessions

# Via daemon commands
/sandbox new                    # Spin up a code sandbox
/desktop new                    # Spin up a desktop sandbox (with display)
/desktop browse https://example.com  # Open browser in desktop sandbox
/desktop screenshot             # Capture current screen
/desktop click 512 384          # Click at coordinates
/desktop type "hello world"     # Type text
/desktop key Return             # Send key
/shell ls -la                   # Run shell command in sandbox
/sandbox kill                   # Terminate sandbox

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                    SolanaOS Daemon                               │
│                                                                  │
│  ┌──────────────────┐  ┌─────────────────┐  ┌───────────────┐  │
│  │  E2B Client       │  │  Desktop Client  │  │ Browser Agent │  │
│  │  (code sandbox)   │  │  (desktop VNC)   │  │ (autonomous)  │  │
│  │                   │  │                  │  │               │  │
│  │  • RunCode()      │  │  • Screenshot()  │  │ • Vision LLM  │  │
│  │  • RunCommand()   │  │  • Click()       │  │ • Action LLM  │  │
│  │  • ListSandboxes  │  │  • TypeText()    │  │ • Tool Exec   │  │
│  │  • KillSandbox()  │  │  • SendKey()     │  │ • OODA Loop   │  │
│  │                   │  │  • OpenBrowser() │  │               │  │
│  └──────┬───────────┘  │  • RunShell()    │  └──────┬────────┘  │
│         │              │  • Scroll()      │         │           │
│         │              │  • Stream()      │         │           │
│         │              └────────┬─────────┘         │           │
│         │                       │                    │           │
│  ┌──────┴───────────────────────┴────────────────────┴────────┐ │
│  │                    E2B REST API                             │ │
│  │              https://api.e2b.dev/sandboxes                 │ │
│  └────────────────────────────────────────────────────────────┘ │
│                                                                  │
│  ┌────────────────────────────────────────────────────────────┐ │
│  │                  Browser Use Integration                    │ │
│  │                                                             │ │
│  │  Cloud Providers:                                          │ │
│  │  • Browser Use API  (BROWSERUSE_API_KEY)                   │ │
│  │  • Browserbase      (BROWSERBASE_API_KEY)                  │ │
│  │                                                             │ │
│  │  Features:                                                  │ │
│  │  • CDP-based browser control                               │ │
│  │  • Cloud session management                                │ │
│  │  • Headed/headless modes                                   │ │
│  │  • Profile persistence                                     │ │
│  │  • Proxy support                                           │ │
│  └────────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘

Sandbox Types

Code Sandbox (Default)

Standard E2B code interpreter — Python execution, file I/O, shell commands. No display.

/sandbox new                    # Create code sandbox
/run print("hello world")      # Execute Python
/shell pip install requests     # Install packages
/sandbox kill                   # Terminate

Desktop Sandbox

Full Linux desktop with X11 display, VNC streaming, mouse/keyboard control.

/desktop new                    # Create desktop sandbox
/desktop screenshot             # Capture screen
/desktop click 100 200          # Click at (100, 200)
/desktop type "search query"    # Type text
/desktop key ctrl+a             # Send key combo
/desktop browse https://...     # Open browser
/desktop kill                   # Terminate

Browser Use Cloud Session

Cloud-hosted browser via Browser Use or Browserbase APIs.

/browseruse connect             # Start cloud browser session
/browseruse open https://...    # Navigate
/browseruse close               # End session

Autonomous Computer Use (Browser Agent)

The Browser Agent combines vision LLMs with desktop control for autonomous task completion.

Agent Loop (OODA)

1. OBSERVE:  Take screenshot of desktop
2. ORIENT:   Send screenshot to vision LLM with objective
3. DECIDE:   LLM analyzes screen, determines next action
4. ACT:      Execute action (click, type, command, etc.)
5. REPEAT:   Until objective is complete or max steps reached

Supported LLM Providers for Vision

The agent supports multiple vision LLM providers (configured via daemon):

ProviderModelsCapabilities
OpenAIGPT-4o, GPT-4o-miniVision + Action
AnthropicClaude 3.5 SonnetVision + Action
GoogleGemini 2.0 FlashVision + Action
GroqLlama 3.2Vision + Action
OpenRouterQwen 2.5 VL, Llama 3.2Vision
FireworksLlama 3.2Vision
MistralPixtralVision

Agent Tools

ToolDescriptionParameters
clickLeft-click at coordinatesx, y
double_clickDouble-click at coordinatesx, y
right_clickRight-click at coordinatesx, y
type_textType text into active inputtext
send_keySend key or combokey (e.g. "Return", "ctrl+c")
run_commandExecute shell commandcommand
open_browserOpen browser to URLurl
scrollScroll mouse wheelx, y, clicks
screenshotCapture screen state—
stopMark task as complete—

Daemon Integration

Chat Commands

CommandDescription
/sandbox [new|kill|list]Manage code sandboxes
/run <code>Execute Python in sandbox
/shell <command>Execute shell in sandbox
/desktop [new|kill|screenshot|click|type|key|browse]Desktop sandbox control
/browseruse [connect|open|close|status]Browser Use sessions
/agent browse <objective>Start autonomous browser agent

Natural Language Detection

The daemon detects sandbox-related intents from natural language:

  • "spin up a sandbox" → /sandbox new
  • "open a browser and go to..." → /desktop browse <url>
  • "take a screenshot" → /desktop screenshot
  • "run this code" → /run <code>

Playwright Integration

For structured E2E testing (vs. autonomous browsing), use the browse skill:

# Playwright tests run against the desktop sandbox
PLAYWRIGHT_BASE_URL="https://<sandbox-id>-8080.e2b.dev" npx playwright test

# Or against Browser Use cloud session
PLAYWRIGHT_CDP_URL="wss://..." npx playwright test --connect

Environment Variables

VariableRequiredDescription
E2B_API_KEYYesE2B API key for sandbox creation
BROWSERUSE_API_KEYNoBrowser Use cloud API key
BROWSERBASE_API_KEYNoBrowserbase API key (alternative)
BROWSERBASE_PROJECT_IDNoBrowserbase project ID
ANTHROPIC_API_KEYNoFor vision/action LLM (Claude)
OPENAI_API_KEYNoFor vision/action LLM (GPT-4o)
GROQ_API_KEYNoFor vision/action LLM (Llama)
OPENROUTER_API_KEYNoFor vision LLM (multi-model)

API Reference

E2B REST API

POST   /sandboxes              Create sandbox
GET    /sandboxes              List sandboxes
DELETE /sandboxes/:id          Kill sandbox
POST   /sandboxes/:id/code     Execute code
POST   /sandboxes/:id/commands Run shell command
GET    /sandboxes/:id/screenshot  Capture desktop (desktop template)
POST   /sandboxes/:id/timeout  Extend timeout

Browser Use API

POST   https://api.browser-use.com/api/v2/browsers          Create session
PATCH  https://api.browser-use.com/api/v2/browsers/:id      Stop session

Browserbase API

POST   https://api.browserbase.com/v1/sessions              Create session
POST   https://api.browserbase.com/v1/sessions/:id          Close session

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

1password

무료

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks SolanaOS to add a note, list notes, search notes, or manage note folders.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

Create, search, and manage Bear notes via grizzly CLI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

blucli

무료

BluOS CLI (blu) for discovery, playback, grouping, and volume.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

x402agent/SolanaOS92026년 7월 23일 업데이트

x402agent의 스킬 모두 보기

이 스킬의 문제 신고