Agentic Browser: ~98% fewer tokens than HTML for LLM web agents (Python + MCP)
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.
Why it exists
Traditional scrapers hand models 100k+ tokens of markup. Agents need:
- Small structured observations (roles, labels, refs)
- Actions that mean success (URL/DOM outcomes)
- A plug-in for any host (MCP + OpenAI/Anthropic tool schemas)
Measured token efficiency
| 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% |
Features
- Stable refs + scoped grounding
- Outcome verification (e.g. Issues click only OK if URL is
/issues) - Page gates for challenges (detect & report - not a bypass tool)
- MCP server for Cursor / Claude Desktop
tools_as_openai()/tools_as_anthropic()- 118 automated tests; milestones M1-M10
Install
pip install agent-browser
playwright install chromium
agent-browser --help
# MCP
python -m agent_browser.mcp
Links
- GitHub: https://github.com/applejuice093/Agentic-browser
- Release: https://github.com/applejuice093/Agentic-browser/releases/tag/v0.4.0
MIT - Python 3.11+
Comments
No comments yet. Start the discussion.