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

A developer released Bruster, an open-source browser automation tool written in Rust that drives the platform's native webview instead of bundling a full Chrome instance, targeting AI agents and scripts. The controller runs without Node.js and exposes both an MCP interface for AI clients like Claude Code and Cursor and JSON lines over stdin/stdout for scripts. In a published Linux benchmark against agent-browser 0.40.0 running full Chrome, Bruster reached a first loaded page in a median 219 ms versus 799 ms and used 256 MiB of idle PSS memory versus 523 MiB, though the author notes the results are workload-specific and span different browser engines.

I've been building Bruster https://github.com/aliilyas/bruster - an open-source browser automation tool written in Rust, designed for AI agents and scripts. The goal is simple: fast startup, lower memory usage, and a straightforward way to control a real browser. Bruster uses your platform’s native webview: The controller runs without Node.js and exposes two interfaces: MCP for compatible AI clients and JSON lines over stdin/stdout for scripts. You can connect it to Claude Code, Cursor, or another MCP-compatible client. The demo is a scripted MCP session showing navigation, form interaction, and screenshots. Here’s one published Linux benchmark comparing Bruster with agent-browser 0.40.0 using full Chrome : | Metric, median | Bruster | agent-browser | |---|---|---| | Launch to first loaded page | 219 ms | 799 ms | | Total idle memory, PSS | 256 MiB | 523 MiB | That run used Ubuntu 24.04 and ten fresh sessions per configuration against local test pages. Memory includes browser helper processes and Bruster’s Xvfb display; Xvfb startup is excluded from timing. These are workload-specific results across different browser engines. The full benchmark report https://aliilyas.github.io/bruster/benchmarks/runs/852486658ea5336c158a06fac49332706e2e3c39-40658586503-1/ includes additional tools, workloads, and methodology. Install on macOS or Linux, then register the MCP server: curl -fsSL https://raw.githubusercontent.com/aliilyas/bruster/main/install.sh | sh claude mcp add bruster -- "$HOME/.local/bin/bruster" --mcp --quiet Linux requires WebKitGTK 4.1, plus xvfb and xauth when running without a desktop display. Platform setup and other MCP clients https://aliilyas.github.io/bruster/mcp/ . Then try: Use Bruster to open https://example.com https://example.com , inspect the page, and take a screenshot. Current limitations include synthetic input events and no cross-origin iframe access. Bruster is MIT licensed , and feedback is welcome—especially on real-world agent workflows and MCP compatibility.