接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @arcede/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
AIR_API_KEY=<secret> claude mcp add io.github.arcededev-air-sdk -- npx -y @arcede/air-sdk@0.2.12在終端機中執行。
{ "mcpServers": { "io.github.arcededev-air-sdk": { "command": "npx", "args": [ "-y", "@arcede/[email protected]" ], "env": { "AIR_API_KEY": "<secret>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令？ 兩種安裝方式的差異
來自發布者
Your browser agent wastes tokens and time every time it asks an LLM what to click. AIR SDK replaces guessing with knowing. This is an early research preview.
Up to 7,000x cost reduction and 280x faster vs frontier models. One function call. Zero code changes.
Measured across 8 major domains, 40 cold API calls, cache disabled. LLM baseline priced at Frontier Model ($15/$75 per M tokens). AIR SDK at Scale tier ($149/mo, 250K executions).
Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.
The more complex the workflow, the more you save. LLM costs compound — every action adds to the conversation context, making each subsequent round trip more expensive. AIR's macro path is always one API call, regardless of how many steps the workflow has.
LLM baseline: Agent inspects page DOM, reasons about which elements to interact with, generates tool calls. Frontier Model pricing ($15/M input, $75/M output).
AIR SDK macro path: Pre-verified CSS selectors returned via API. Agent executes directly — no DOM inspection, no LLM reasoning. Cost = plan price / included executions.
Raw API latency (40 measurements, cache disabled):
Cost per action by tier:
Capabilities discovered: 16 avg per domain (range: 3–39)
Last run: 2026-03-20 | Run benchmark yourself: npx tsx benchmark/run.ts
npm install @arcede/air-sdk
npx @arcede/air-sdk init # saves key to ~/.config/air/credentials.json
Agent Skill (recommended for AI coding agents):
npx @arcede/air-sdk install-skill # auto-configures Claude Desktop, Claude Code, Cursor, Windsurf, OpenClaw
Free tier included. No credit card. Make the network smarter, star the repo and share it ⭐
Don't need the full SDK? We publish standalone packages for common use cases:
Wrap your existing Playwright page. Nothing else changes.
import { chromium } from 'playwright';
import { withAIR } from '@arcede/air-sdk/playwright';
const browser = await chromium.launch();
const page = await browser.newPage();
const smartPage = withAIR(page, { apiKey: process.env.AIR_API_KEY });
// Your existing code — now with site intelligence
await smartPage.goto('https://example.com');
await smartPage.fill('#search', 'flights to tokyo');
await smartPage.click('.search-btn');
// Know what's possible on any site before writing automation
const capabilities = await smartPage.air.listCapabilities('example.com');
Also works with Puppeteer and Browser Use:
// Puppeteer
import { withAIR } from '@arcede/air-sdk/puppeteer';
const page = withAIR(await browser.newPage(), { apiKey: process.env.AIR_API_KEY });
// Browser Use
import { AIRPlugin } from '@arcede/air-sdk/browser-use';
const agent = Agent({ plugins: [new AIRPlugin({ apiKey: process.env.AIR_API_KEY })] });
Browser automation is fragile. Selectors break. Sites change. Your agent has no idea what's possible until it's already on the page.
AIR SDK gives your agent three things:
How it works: Wrap your page with withAIR(). The SDK observes actions, resolves selectors, and preloads site capabilities. Your code doesn't change — it just works better.
Privacy-first: Input values, cookies, and PII are never sent. See our privacy docs →
API keys are stored at ~/.config/air/credentials.json with 0600 permissions (owner read/write only).
npx @arcede/air-sdk init # Save your key (opens dashboard)
npx @arcede/air-sdk whoami # Show current key, source, and agent status
npx @arcede/air-sdk logout # Remove key from all locations
Key resolution order: AIR_API_KEY env var → ~/.config/air/credentials.json → .env in current directory.
Give your coding agent site intelligence with one command:
npx @arcede/air-sdk install-skill
This auto-detects Claude Desktop, Claude Code, Cursor, Windsurf, and OpenClaw, writes the MCP server config, and injects your API key. It installs @arcede/air-sdk globally for fast agent startup (~2s instead of ~60s with npx) and writes the absolute binary path to each config to avoid npx version caching issues. Restart your agent and it instantly has new tools.
Requires global install:
npm install -g @arcede/air-sdk. If not installed globally, replace"command": "air-sdk"with"command": "npx"and"args": ["--mcp"]with"args": ["-y", "@arcede/air-sdk", "--mcp"].
Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"air-sdk": {
"command": "air-sdk",
"args": ["--mcp"],
"env": { "AIR_API_KEY": "air_xxx" }
}
}
}
Claude Code:
claude mcp add air-sdk -e AIR_API_KEY=your_key_here -- air-sdk --mcp
Cursor — add to ~/.cursor/mcp.json:
{
"mcpServers": {
"air-sdk": {
"command": "air-sdk",
"args": ["--mcp"],
"env": { "AIR_API_KEY": "air_xxx" }
}
}
}
Windsurf — add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"air-sdk": {
"command": "air-sdk",
"args": ["--mcp"],
"env": { "AIR_API_KEY": "air_xxx" }
}
}
}
OpenClaw — add to ~/.openclaw/openclaw.json:
{
"mcpServers": {
"air-sdk": {
"command": "air-sdk",
"args": ["--mcp"],
"env": { "AIR_API_KEY": "air_xxx" }
}
}
}
Tools available:
AIR SDK is also available as an OpenAI hosted shell skill for gpt-5.4 and gpt-5.4-mini:
# Package and upload
cd air-sdk/openai-skill
zip -r /tmp/air-sdk-skill.zip .
curl -X POST 'https://api.openai.com/v1/skills' \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-F 'files=@/tmp/air-sdk-skill.zip'
Then use in the Responses API:
{
"model": "gpt-5.4-mini",
"tools": [{
"type": "shell",
"environment": {
"type": "container_auto",
"skills": [{ "type": "skill_reference", "skill_id": "<your_skill_id>" }],
"network_policy": {
"type": "allowlist",
"allowed_domains": ["agentinternetruntime.com", "api.agentinternetruntime.com"],
"domain_secrets": [
{ "domain": "api.agentinternetruntime.com", "name": "AIR_API_KEY", "value": "<key>" },
{ "domain": "api.agentinternetruntime.com", "name": "Authorization", "value": "Bearer <key>" }
]
}
}
}]
}
Requires api.agentinternetruntime.com in your org network allowlist.
withAIR(page, {
apiKey: process.env.AIR_API_KEY, // Required
cacheEnabled: true, // Local capability cache (default: true)
cacheTTLMs: 1_800_000, // Cache TTL in ms (default: 30 min)
debug: false, // Log debug info (default: false)
});
AIR SDK supports x402 micropayments, enabling your agent to pay for premium site access without pre-registration:
const smartPage = withAIR(page, {
apiKey: process.env.AIR_API_KEY,
mpp: {
enabled: true,
paymentMethod: 'stripe_spt',
credential: 'spt_...',
maxPerRequest: 0.50,
maxPerSession: 5.00,
autoApprove: true,
},
});
See examples/agents/ for working agent examples:
See CONTRIBUTING.md. PRs welcome.
Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.
{ "mcpServers": { "io.github.arcededev-air-sdk": { "command": "npx", "args": [ "-y", "@arcede/[email protected]" ], "env": { "AIR_API_KEY": "<secret>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數：AIR_API_KEY。
AIR SDK 透過 stdio 在本機執行。
上次檢查時間：2026-11-08。 Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.