https://github.com/browserbase/open-operator
https://github.com/browserbase/open-operator
Last synced: 6 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/browserbase/open-operator
- Owner: browserbase
- Created: 2025-01-23T23:36:18.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-06T00:31:17.000Z (about 1 year ago)
- Last Synced: 2025-02-06T01:24:41.560Z (about 1 year ago)
- Language: TypeScript
- Homepage: https://operator.browserbase.com/
- Size: 780 KB
- Stars: 994
- Watchers: 17
- Forks: 183
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Open Operator
> [!WARNING]
> This is simply a proof of concept.
> Browserbase aims not to compete with web agents, but rather to provide all the necessary tools for anybody to build their own web agent. We strongly recommend you check out both [Browserbase](https://www.browserbase.com) and our open source project [Stagehand](https://www.stagehand.dev) to build your own web agent.
[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fbrowserbase%2Fopen-operator&env=OPENAI_API_KEY,BROWSERBASE_API_KEY,BROWSERBASE_PROJECT_ID&envDescription=API%20keys%20needed%20to%20run%20Open%20Operator&envLink=https%3A%2F%2Fgithub.com%2Fbrowserbase%2Fopen-operator%23environment-variables)
## Getting Started
First, install the dependencies for this repository. This requires [pnpm](https://pnpm.io/installation#using-other-package-managers).
```bash
pnpm install
```
Next, copy the example environment variables:
```bash
cp .env.example .env.local
```
You'll need to set up your API keys:
1. Get your OpenAI API key from [OpenAI's dashboard](https://platform.openai.com/api-keys)
2. Get your Browserbase API key and project ID from [Browserbase](https://www.browserbase.com)
Update `.env.local` with your API keys:
- `OPENAI_API_KEY`: Your OpenAI API key
- `BROWSERBASE_API_KEY`: Your Browserbase API key
- `BROWSERBASE_PROJECT_ID`: Your Browserbase project ID
Then, run the development server:
```bash
pnpm dev
```
Open [http://localhost:3000](http://localhost:3000) with your browser to see Open Operator in action.
## How It Works
Building a web agent is a complex task. You need to understand the user's intent, convert it into headless browser operations, and execute actions, each of which can be incredibly complex on their own.
Stagehand is a tool that helps you build web agents. It allows you to convert natural language into headless browser operations, execute actions on the browser, and extract results back into structured data.
Under the hood, we have a very simple agent loop that just calls Stagehand to convert the user's intent into headless browser operations, and then calls Browserbase to execute those operations.
Stagehand uses Browserbase to execute actions on the browser, and OpenAI to understand the user's intent.
For more on this, check out the code at [this commit](https://github.com/browserbase/open-operator/blob/6f2fba55b3d271be61819dc11e64b1ada52646ac/index.ts).
### Key Technologies
- **[Browserbase](https://www.browserbase.com)**: Powers the core browser automation and interaction capabilities
- **[Stagehand](https://www.stagehand.dev)**: Handles precise DOM manipulation and state management
- **[Next.js](https://nextjs.org)**: Provides the modern web framework foundation
- **[OpenAI](https://openai.com)**: Enable natural language understanding and decision making
## Contributing
We welcome contributions! Whether it's:
- Adding new features
- Improving documentation
- Reporting bugs
- Suggesting enhancements
Please feel free to open issues and pull requests.
## License
Open Operator is open source software licensed under the MIT license.
## Acknowledgments
This project is inspired by OpenAI's Operator feature and builds upon various open source technologies including Next.js, React, Browserbase, and Stagehand.