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

Agentic Browser, an agent-first Python browser built on Playwright/Chromium, reduces token consumption for LLM web agents by up to 99.4% compared to raw HTML. It provides compact observations, stable element references, and outcome-verified actions, with reductions from ~225,000 tokens to ~1,300 tokens on complex pages like the Rockstar GTA VI landing page.

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+