Browsernode connects AI agents to the browser using a TypeScript implementation compatible with Browser-use APIs. This review summarizes setup steps, code examples, and basic usage from the README.

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (2 so far).
What it is
Browsernode is a TypeScript implementation that connects AI agents with the browser and is compatible with all Browser-use APIs and features.
How it works
It provides an Agent class and llm integrations (e.g., ChatOpenAI) to run a task in a browser context. Examples show creating an llm, constructing an Agent with a task, and running agent.run().
Getting started
Install with npm:
npm install browsernode
Install Playwright:
npm init playwright@latest
playwright install chromium
Add API keys to .env (example file and env var):
mv .env.example .env
OPENAI_API_KEY=
From the README, additional usage shows two styles:
CommonJS:
const { Agent } = require("browsernode");
const { ChatOpenAI } = require("browsernode/llm");
(async () => {
const llm = new ChatOpenAI({
model: "gpt-4.1",
temperature: 0.0,
apiKey: process.env.OPENAI_API_KEY,
});
const task = "Search for the latest tesla stock price";
const agent = new Agent({
task,
llm,
});
const history = await agent.run();
console.log(history.usage);
})();
ESM:
import { Agent } from "browsernode";
import { ChatOpenAI } from "browsernode/llm";
const llm = new ChatOpenAI({
model: "gpt-4.1",
temperature: 0.0,
apiKey: process.env.OPENAI_API_KEY,
});
const task = "Search for the latest tesla stock price";
const agent = new Agent({
task: task,
llm: llm,
});
agent.run();
Run example script:
npx tsx quickstart.ts
Recent releases
RELEASES (latest 0): - none
Traction
Stars: 1056, Forks: 111, Open issues: 2
Behind the repo
Not specified in the provided content.
Caveats
License: MIT Created: 2025-06-23 Last push: 2025-08-06






