botbrowser
v0.1.1
Published
Token-efficient web content extraction for LLM agents
Maintainers
Readme
BotBrowser
Token-efficient web browser for LLM agents.
A typical web page is 50,000+ tokens. The useful content? 2,000–5,000 tokens. BotBrowser strips the bloat and gives your agents clean markdown — saving 90–95% of tokens.
Install
npm install botbrowserQuick Start
import { extract } from 'botbrowser';
const result = await extract('https://example.com/article');
console.log(result.content); // clean markdown
console.log(result.metadata.tokenSavingsPercent); // 94Features
- Token-first — 90–95% token reduction on real-world pages
- Zero config — No API key, no server, no setup
- Clean markdown — Headings, lists, tables, code blocks preserved
- Smart extraction — Strips nav, ads, footers, and boilerplate automatically
- Fast — Pure HTML parsing, no browser required
Links
License
MIT
