# Agentic Browser: ~98% fewer tokens than HTML for LLM web agents (Python + MCP)

> Source: <https://dev.to/tophet_cafd932aa262f4fc92/agentic-browser-98-fewer-tokens-than-html-for-llm-web-agents-python-mcp-1onj>
> Published: 2026-07-17 09:16:13+00:00

Agentic Browser is an **agent-first Python browser** built on Playwright/Chromium so LLMs can drive the web with **compact observations**, **stable element refs**, and **outcome-verified actions** ? not raw HTML dumps.

Traditional scrapers hand models 100k+ tokens of markup. Agents need:

| Scenario | Raw HTML | Compact observation | Reduction |
|---|---|---|---|
| Quotes scrape | ~2.8k?6.2k | ~0.45k?1.3k | ~78?84% |
| Rockstar GTA VI landing | ~225,000 | ~1,300 | ~99.4% |
GitHub `vercel/next.js`
|
~110,000 | ~1,900 | ~98.3% |

`/issues`

)`tools_as_openai()`

/ `tools_as_anthropic()`

```
pip install agent-browser
playwright install chromium
agent-browser --help
# MCP
python -m agent_browser.mcp
```

MIT ? Python 3.11+