Compact semantic trees and agent-ready page checks from HTML, URLs, WebViews, and live browser pages.
Core features:
- readable semantic trees from URLs, files, stdin, or captured browser HTML
- compact
--agentJSON for search, page checks, and browser handoff loops
curl -fsSL https://raw.githubusercontent.com/hmmhmmhm/ax-grep/main/skills.sh | shThe skill prompt teaches subagents to call ax-grep before opening a browser:
npx ax-grep https://example.com
npx ax-grep https://example.com --agentnpm install ax-grepimport { extract, formatSemanticTreeText } from "ax-grep";
const html = await fetch("https://example.com").then((r) => r.text());
const tree = extract(html);
const promptText = formatSemanticTreeText(tree);import { createExtractorScript } from "ax-grep";
const script = createExtractorScript({ format: "text" });
// Playwright/Puppeteer: await page.evaluate(script)
// iOS/Android WebView: evaluateJavaScript(script)