Skip to content

Github · GitHub Repository Radar

lennybase browsernode

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Stars

1,055

Inactive

Forks

111

Watchers: 1,055

Repository Radar Score

31 / 100

Growth

7d
+0
30d
+0
%
0.0%

Not enough metric snapshots yet to chart growth for this repository.

Score breakdown

  • popularity 54
  • growth 0
  • activity 15
  • freshness 100
  • community 20

Need help integrating this stack?

Our team builds with modern open-source stacks. Tell us what you are shipping.

Get a quote →
Shows a black Browser Use Logo in light color mode and a white one in dark color mode.

Enable AI to control your browser 🤖

Browsernode is TypeScript implementation of Browser-use

🌐 Browsernode is the easiest way to connect your AI agents with the browser. ✅ Browsernode is compatible with all of Browser-use APIs and features.

Quick start

with Node.js (v20.19.4 or higher) and npm

❌ Bun environment , has a Playwright bug.

npm install browsernode

Install Playwright: Installation | Playwright

npm init playwright@latest
playwright install chromium

Add your API keys for the provider you want to use to your .env file.

mv .env.example .env
OPENAI_API_KEY=

For other settings, models, and more, check out the documentation 📕.

Spin up your agent:

Commonjs style

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 style

package.json

{
  // ... other properties
  "type": "module"
  // ... other properties
}
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

npx tsx quickstart.ts

Test with UI

You can test browsernode using gadio_demo

Test with an interactive CLI

You can also use our browsernode-cli

Demos

Task:look up the world's most valuable companies, save top 5 companies and their value to companies.txt.

AI Did Search And Save

output: companies.txt

1. Microsoft: $3.530 T
2. NVIDIA: $3.462 T
3. Apple: $2.934 T
4. Amazon: $2.251 T
5. Alphabet (Google): $2.125 T



Task:Write a letter in Google Docs to my Papa, thanking him for everything, and save the document as a PDF.

Write google doc And Save pdf



Task:go to https://en.wikipedia.org/wiki/Banana and click on buttons on the wikipedia page to go as fast as possible from banna to Quantum mechanics

from banana to Quantum mechanics result:

// ... previous actions
🛠️ Action 1/1: {
  "clickElement": {
    "index": 41
  }
}
// ... more actions
 🛠️ Action 1/1: {
"done": {
    "success": false,
    "text": "I navigated through the Banana Wikipedia page, reaching the section on Fusarium wilt TR4. However, I did not complete the task of reaching Quantum mechanics."
  }
}
// ... final result
📄 Result: I navigated through the Banana Wikipedia page, reaching the section on Fusarium wilt TR4. However, I did not complete the task of reaching Quantum mechanics.



More examples

For more examples see the examples folder

Contributing

We love contributions! Feel free to open issues for bugs or feature requests. To contribute to the docs, check out the /docs folder.

Created: Jun 23, 2025

Last push: Aug 6, 2025

Default branch: main

Languages

Share of the codebase by language, based on repository metadata from the host.

  • TypeScript 84.8%
  • JavaScript 15.2%

Repository Radar analysis

Deterministic insights derived from public metadata and our observations — not personal testing or reviews.

Why this repository is interesting

  • Listed in our discovery index with public GitHub metadata for analysis.

Who should use it

  • Developers working primarily with TypeScript
  • Teams exploring AI tooling, agents, or ML infrastructure

Potential use cases

  • Reference or evaluate TypeScript open-source approaches in this domain
  • Prototype AI/agent workflows or study reference architectures

Strengths

  • README present in our index
  • Declared license: MIT License

Limitations / considerations

  • Insights are derived from public metadata and our observations — not a substitute for code review

What to watch

  • Radar Score is modest — dig into activity and docs before committing

Source: GitHub (public metadata) + Repository Radar analysis. We do not claim ownership of third-party repositories.

Ready to ship something that compounds?

Share your roadmap. We’ll come back with scope options, timeline ranges, and who from Shriram IT Ventures should be in the room.

Popular with product teams