The browser interface AI agents deserve.

AWI is an MCP server that gives AI agents a compact, semantic view of any web page — not 40,000 bytes of DOM they can't reason over.

  • Stable element IDs
  • Token-efficient snapshots
  • No raw DOM noise
$npx agent-web-interface install
View on GitHub
  • Open source
  • MIT licensed
  • Works with Claude, GPT-4o, Gemini, Ollama
  • Requires Node.js + Chrome

The Problem

Browser automation is easy for scripts.

Hard for agents.

Current tools dump thousands of tokens of noise into the agent's context. Tasks fail mid-flow. Selectors break on the next deploy. And there's no stable way to reference an element across calls.

Browser output comparison: Raw DOM and Accessibility Tree fail agents; Agent Web Interface succeeds.

Raw DOM

<div class="wrapper xyz-123">
  <div class="inner" data-v="8">
    <button type="submit"
      class="btn btn-primary
      x-4 y-2 md:x-6">
      Submit
    </button>
  </div>
</div>

40,000+ bytes of noise. Brittle class selectors. Context exhaustion.

Accessibility Tree

RootWebArea "Checkout"
  generic ""
    generic "wrapper xyz-123"
      generic "inner"
        button "Submit"
          StaticText "Submit"

Better, but still verbose. No stable IDs to reference across calls.

Agent Web Interface

<page title="Checkout">
  <region role="main">
    <button
      eid="btn-1"
      label="Submit" />
  </region>
</page>

Compact. Stable eid. Only what the agent needs.

Live Example

See what your agent sees.

Every MCP tool call returns a structured semantic snapshot — not raw DOM.

agent-web-interface

input → tool call

{
  "tool": "navigate",
  "params": {
    "url": "https://example.com/checkout"
  }
}

output → snapshot

<page url="https://example.com/checkout"
      title="Checkout">
  <region role="main">
    <heading level="1">Your Cart (3 items)</heading>
    <list>
      <item eid="p1">Widget Pro — $29.99</item>
      <item eid="p2">Widget Lite — $9.99</item>
    </list>
    <button eid="btn-checkout"
            label="Proceed to Payment" />
  </region>
</page>

The agent references btn-checkout by eid across every call that follows — no selector hunting, no re-finding elements after navigation.

How It Works

Five steps. One install command.

1

Agent calls a browser tool via MCP

navigate, click, find, type, screenshot…

2

AWI intercepts the tool call

A local server launched with npx — no daemon to manage

3

Puppeteer drives Chrome

Local Chrome via CDP — real rendering, full JS

4

Page reduced to semantic XML

Headings, buttons, links, forms — no raw markup

5

Agent receives stable eids

Reference the same button call after call. No re-finding elements.

AWI runs locally and needs Node.js and Chrome. For serverless or shared deployments, see AWI Cloud.

Features

What agents get that Playwright doesn't.

Semantic Snapshots

Regions, headings, links, buttons — not a wall of DOM. Agents reason over structure, not markup.

Stable Element IDs

Every interactive element gets a stable eid. Reference it across 10 tool calls — CSS classes change on the next deploy, eid doesn't.

Token-Efficient

Snapshots return only the structure an agent needs to act — not the full page on every call. Longer task horizons. Lower token spend.

Network Inspection

See every request that followed an action — verify form submissions, trace auth flows, and debug redirects without a DevTools tab.

Canvas Inspection

When the page is a canvas, chart, or image, capture a screenshot or read canvas data directly. Semantic snapshots where they work; pixels where they don't.

Model-Agnostic

Works with any MCP-compatible agent runtime: Claude, GPT-4o, Gemini, local models. No vendor lock-in.

What People Build

Agents that act on the live web.

Web Research Agents

Navigate, read, and extract from live pages — pricing monitors, news aggregators, and competitor trackers that work on real rendered content, not stale APIs.

QA & Flow Automation

Walk through sign-up, checkout, and onboarding flows. Fill forms, verify responses — without the fragile CSS selectors that break Playwright suites.

Data Entry & Form Filling

Log in, find fields by their label, and submit — even on pages where the DOM shifts between visits.

Managed Cloud

Don't want to manage Chrome?

AWI Cloud runs headless Chrome for you. Connect via API key in seconds, share sessions across your team, and pay only for the browser time you use.

  • No local Chrome or Node.js to install — just an API key
  • Share browser sessions and credentials across your team
  • Pay by the minute — no seat fees, no commitments
  • Start free, upgrade when you scale

FAQ

Questions agents (and their developers) ask.

What is Agent Web Interface (AWI)?

AWI is an open-source MCP server that gives AI agents a compact, semantic view of any web page. Instead of raw DOM or verbose accessibility trees, it returns structured XML snapshots with stable element IDs (eids) that agents can reference across tool calls.

How is AWI different from Playwright or Puppeteer MCP servers?

Playwright and Puppeteer were built for deterministic scripts, so their MCP wrappers hand an agent raw DOM or long accessibility dumps that flood its context. AWI returns only the semantic structure an agent needs — headings, buttons, links, forms — with stable eids, so tasks run longer on far fewer tokens.

How does AWI reduce token usage?

A typical page is 40,000+ bytes of DOM. AWI reduces it to a compact snapshot — often under 1 KB — containing only the interactive and structural elements an agent needs to act. That means fewer tokens per step and longer multi-step tasks before the context fills up.

Which AI models and agents does AWI work with?

Any MCP-compatible runtime — Claude, GPT-4o, Gemini, and local models via Ollama. AWI speaks the Model Context Protocol directly, so there is no model-specific glue code and no vendor lock-in.

Is AWI free and open source?

Yes. AWI is MIT-licensed and developed in the open on GitHub, so you can self-host it for free. A managed AWI Cloud is available for teams that would rather not run Chrome themselves.

Do I need to run a browser locally?

The local server drives a real Chrome instance through Puppeteer, so you need Node.js and Chrome installed. If you would rather not manage that, AWI Cloud runs headless Chrome for you behind an API key.

Get Started

One command. Agents browsing.

$npx agent-web-interface install

Open source · MIT licensed · Works with Claude, GPT-4o, Gemini, and any MCP-compatible agent.