Bruster: A Faster-Starting, Lighter Browser for AI Agents

说明与用途

Bruster是一款基于Rust编写的开源浏览器自动化工具，专为AI代理和脚本设计。它使用原生webview（macOS为WKWebView，Linux为WebKitGTK，Windows为WebView2），提供MCP和JSON over stdin/stdout接口。在Linux上发布的基准测试中，Bruster的启动速度更快（219毫秒 vs. 799毫秒），内存占用更低（256 MiB vs. 523 MiB PSS），优于agent-browser 0.40.0。

问题

AI agents and scripts need a fast-starting, low-memory browser automation tool that works with native webviews and MCP clients.

结果

Bruster achieves faster startup (219 ms vs. 799 ms) and lower memory (256 MiB vs. 523 MiB PSS) than agent-browser 0.40.0 in a published Linux benchmark on Ubuntu 24.04.

工作流

• Install Bruster via install.sh on macOS or Linux
• Register the MCP server with Claude Code or another MCP-compatible client
• Use Bruster to navigate websites, inspect page content, click elements, fill forms, submit forms, capture screenshots, and manage tabs/sessions

证据

The goal is simple: fast startup, lower memory usage, and a straightforward way to control a real browser.

来源

Here’s one published Linux benchmark comparing Bruster with agent-browser 0.40.0 using full Chrome: Launch to first loaded page: 219 ms vs. 799 ms; Total idle memory, PSS: 256 MiB vs. 523 MiB.

来源

Linux requires WebKitGTK 4.1, plus xvfb and xauth when running without a desktop display.

来源

Current limitations include synthetic input events and no cross-origin iframe access.

来源