过去一年，大模型 Agent 的能力边界正在从会聊天、会写代码，快速扩展到会使用真实软件。其中最典型的场景，就是让大模型直接操作 Chrome 浏览器：打开网页、阅读内容、点击按钮、填写表单、上传文件、下载资料，甚至完成跨网页、多步骤的复杂任务。

Browser Use connects AI agents directly to web browsers, enabling them to autonomously navigate, interact with, and extract information from websites. Author’s note: The generative AI revolution has ...

PyScript lets you run Python scripts right in the browser, side by side with JavaScript, with two-way interaction between your code and the web page. Created by Anaconda and launched in April 2022, ...

We may not have an agreed-upon definition of AI “agent” yet, but a multitude of startups want to create “agentic” tools to automate various tasks online. One such firm, Browser Use, has attracted a ...