Build custom browser agents with AI-powered automation. Record browser interactions, extract data, and run complex workflows via a simple API. You can extract data from websites, fill out forms, do QA testing, and more.

• 🎯 Visual Recording: Record browser interactions with the Optexity Recorder Chrome extension
• 🤖 AI-Powered: Uses LLMs to handle dynamic content and find elements intelligently
• 📊 Data Extraction: Extract structured data from web pages using LLM-based extraction
• 🔄 Workflow Automation: Chain multiple actions together for complex browser workflows
• 🚀 API-First: Run automations via REST API with simple JSON requests
• 🎨 Dashboard: Manage and monitor your automations through the Optexity dashboard

Head to dashboard.optexity.com and sign up for a free account.

Once logged in, navigate to the API Keys section in your dashboard and create a new key.

Install the Optexity Recorder extension from the Chrome Web Store. This extension captures your browser interactions and converts them into automation workflows.

• Python 3.11+
• Git

Choose one of the options below.

conda create -n optexity python=3.11
conda activate optexity

Install miniconda here: https://docs.conda.io/projects/conda/en/stable/user-guide/install/index.html#installing-in-silent-mode

python3 -m venv .venv
source .venv/bin/activate

Install Optexity directly from PyPI:

pip install optexity
optexity install-browsers

OR

If you want to clone and edit from source:

git clone git@github.com:Optexity/optexity.git
cd optexity
pip install -e .
optexity install-browsers

API_KEY=YOUR_OPTEXITY_API_KEY # API key used for authenticated requests
GOOGLE_API_KEY=YOUR_GOOGLE_API_KEY # API key used for Google Gemini
DEPLOYMENT=dev # or "prod" in production

You can get your free Google Gemini API key from the Google AI Studio Console.

The fastest way to create an automation is by recording your actions directly in the browser.

1. Navigate to the target website: Open Chrome and go to the website you want to automate (e.g., https://stockanalysis.com/)

2. Start capturing: Click the Optexity Recorder extension icon and hit Start Capture

3. Perform your actions:

   • Click on the "Search" button
   • Enter the stock symbol in the search bar
   • Click on the first result in the search results

4. Stop and save: When finished, click Complete Capture. The automation is automatically saved to your dashboard as a JSON file.

• Perform actions slowly and deliberately for better accuracy
• Avoid unnecessary scrolling or hovering
• The recorder captures clicks, text input, and form selections

The primary way to run browser automations locally is via the inference server.

optexity inference --port 9000 --child_process_id 0

Key parameters:

• --port: HTTP port the local inference server listens on (e.g. 9000).
• --child_process_id: Integer identifier for this worker. Use different IDs if you run multiple workers in parallel.

When this process starts, it exposes:

• GET /health – health and queue status
• GET /is_task_running – whether a task is currently executing
• POST /inference – main endpoint to allocate and execute tasks

With the server running on http://localhost:9000, you can allocate a task by sending an InferenceRequest to /inference.

• endpoint_name: Name of the automation endpoint to execute. This must match a recording/automation defined in the Optexity dashboard.
• input_parameters: dict[str, list[str]] – all input values for the automation, as lists of strings.
• unique_parameter_names: list[str] – subset of keys from input_parameters that uniquely identify this task (used for deduplication and validation). Only one task with the same unique_parameter_names will be allocated. If no unique_parameter_names are provided, the task will be allocated immediately.

curl -X POST http://localhost:9000/inference \
 -H "Content-Type: application/json" \
 -d '{
 "endpoint_name": "extract_price_stockanalysis",
 "input_parameters": {
 "search_term": ["NVDA"]
 },
 "unique_parameter_names": []
 }'

On success, the inference server:

1. Forwards the request to your control plane at api.optexity.com using INFERENCE_ENDPOINT (defaults to api/v1/inference).
2. Receives a serialized Task object from the control plane.
3. Enqueues that Task locally and starts processing it in the background.
4. Returns a 202 Accepted response:

{
 "success": true,
 "message": "Task has been allocated"
}

Task execution (browser automation, screenshots, outputs, etc.) happens asynchronously in the background worker. You can see it running locally in your browser.

You can monitor the task on the dashboard. It will show the status, errors, outputs, and all the downloaded files.

Watch the video

For detailed documentation, visit our documentation site:

• Recording First Automation
• Running First Inference
• Local Setup
• Building Automations
• API Reference

We're actively working on improving Optexity. Here's what's coming:

• 🔜 Self Improvement: Agent adaption using self exploration
• 🔜 More Action Types: Additional interaction and extraction capabilities
• 🔜 Performance Optimizations: Faster execution and reduced resource usage
• 🔜 Advanced Scheduling: Built-in task scheduling and cron support
• 🔜 Cloud Deployment: Simplified cloud deployment options

Have ideas or feature requests? Open an issue or join our Discord to discuss!

We welcome contributions! Here's how you can help:

Found a bug or have a feature request? Please open an issue on GitHub. Include:

• A clear description of the problem
• Steps to reproduce
• Expected vs actual behavior
• Environment details (OS, Python version, etc.)

Have questions, ideas, or want to discuss the project? Use GitHub Discussions to:

• Ask questions
• Share ideas
• Discuss best practices
• Get help from the community

Join our Discord community to:

• Chat with the founders directly
• Get real-time support
• Share your automations
• Connect with other users

Join Discord →

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run pre-commit checks: pre-commit run --all-files
5. Commit your changes (git commit -m 'Add some amazing feature')
6. Push to the branch (git push origin feature/amazing-feature)
7. Open a Pull Request

Check out our examples directory for sample automations:

• I94 extraction
• Healthcare Form Automation
• QA Testing

This project is licensed under the terms specified in the LICENSE file.

• 📖 Documentation
• 💬 Discord Community
• 🐛 Report Issues
• 💭 Discussions
• 📧 Email Support

Made with ❤️ by the Optexity team