Give your AI agent a real browser. 3.2x more token-efficient than Playwright MCP. 6x more than Chrome DevTools MCP.
Give your AI agent a real browser. 3.2x more token-efficient than Playwright MCP. 6x more than Chrome DevTools MCP.
Built different from the ground up.
3.2x fewer tokens than Playwright MCP. 6x fewer than Chrome DevTools MCP. Text, not screenshots.
Works with 12 LLM providers out of the box, plus any OpenAI-compatible endpoint.
One execute_code tool, persistent Python namespace. Navigate, click, type, extract.
Watch your agent browse in real-time via VNC streaming. See every click, scroll, and navigation live.
Docker, Kubernetes, cloud deployment. Battle-tested infrastructure for any scale.
MIT licensed. Community-driven. Fully extensible. Build on top of OpenBrowser.
Star on GitHubFrom zero to autonomous browsing in minutes.
The agent navigates, clicks, types, and extracts data autonomously. Watch it work in real-time through the live browser view.
Watch a real agent browse the web autonomously.
OpenBrowser integrates with any MCP-compatible client.
Be the first to try the hosted version of OpenBrowser.