ArcedeDev/air-sdk
Collective intelligence for agents. Stop your agents from guessing how to use the web. Let them know what to do. Think; hive mind. Let's make the open agent internet.
Platform-specific configuration:
{
"mcpServers": {
"air-sdk": {
"command": "npx",
"args": [
"-y",
"air-sdk"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> <h1 align="center">AIR SDK</h1> <p align="center"> Collective intelligence for agents. Stop your agents from guessing how to use the web. Let them know what to do. Think; hive mind. Let's make the open agent internet. </p> </p>
<p align="center"> <a href="https://www.npmjs.com/package/@arcede/air-sdk"></a> <a href="https://www.npmjs.com/package/@arcede/air-sdk"></a> <a href="https://github.com/ArcedeDev/air-sdk/blob/main/LICENSE"></a> <a href="https://agentinternetruntime.com/docs/sdk"></a> </p>
<p align="center"> <a href="#install">Install</a> · <a href="#quick-start">Quick Start</a> · <a href="#why">Why</a> · <a href="#agent-skill">Agent Skill</a> · <a href="https://agentinternetruntime.com/docs/sdk">Docs</a> </p>
---
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).
| Scenario | LLM DOM Reasoning (Frontier Model) | AIR SDK (Macro Path) | Savings | |----------|-------------------------------|---------------------|---------| | 1 browser action | ~$0.24, ~4s, ~10K tokens (2 LLM rou
Loading reviews...