Browser

Summary

The Browser Agent completes tasks on the live web by driving a real Chromium browser. It uses a snapshot-and-selector loop — the model sees a stable list of interactive elements instead of brittle CSS — to navigate, click, and type. Reach for it to automate flows, scrape interactive pages, or test UIs.

Install

bunnpmpnpmyarn
$ pnpm dlx shadcn@latest add @agentcn/flue/browser-agent
Copy

Composition

Copyagents/
└── browser-agent.ts    # Agent with the four browser tools
tools/
└── browser.ts          # browser_goto / snapshot / click / type
lib/
└── browser.ts          # Shared Playwright page + snapshot helper

Customization

• Use hosted browsers. Set BROWSER_CDP_URL to run against Browserbase or a remote Chrome.
• Richer snapshots. Extend lib/browser.ts to include roles, ARIA, or bounding boxes.
• Add actions. Add tools for scrolling, file uploads, or screenshots.
• Swap the model. Change the model field on the agent.