Mastra

Use Lightcone with Mastra, a TypeScript framework for building AI agents, workflows, and RAG pipelines.

Install

npm install mastra @tzafon/lightcone

Example

import { Agent } from "mastra";
import Lightcone from "@tzafon/lightcone";

const lightcone = new Lightcone();

const browseWebTool = {
  name: "browse_web",
  description: "Visit a URL, interact with the page, and take a screenshot",
  parameters: {
    url: { type: "string" as const, description: "URL to visit" },
  },
  execute: async ({ url }: { url: string }) => {
    const computer = await lightcone.computers.create({ kind: "browser" });
    const id = computer.id!;

    await lightcone.computers.navigate(id, { url });
    const result = await lightcone.computers.screenshot(id);
    await lightcone.computers.delete(id);

    return { screenshot: result.result?.screenshot_url };
  },
};

const agent = new Agent({
  name: "Web Researcher",
  instructions: "You are a helpful assistant that can browse the web.",
  model: { provider: "OPEN_AI", name: "gpt-4o" },
  tools: { browse_web: browseWebTool },
});

const response = await agent.generate(
  "Visit https://news.ycombinator.com and describe the top stories"
);
console.log(response.text);

How it works

Mastra agents use tools to interact with external systems. Lightcone’s browser actions are wrapped as Mastra tools. When the agent decides it needs to visit a web page, it calls the tool, which creates a browser session, performs actions, and returns results.

Resources

• Mastra documentation
• Mastra GitHub

See also

• Vercel AI SDK — another TypeScript AI framework with Lightcone
• LangChain — Python and TypeScript agent tools
• Computers — direct browser control API