# Quickstart

**Welcome to NotexAI 🌌**

NotexAI is a web browser for LLM agents. It transforms the internet into an agent-friendly environment, turning websites into structured, navigable maps described in natural language. By using natural language commands, NotexAI minimizes hallucinations, reduces token usage, and lowers costs and latency.

​ Get an API key Create an account on our console <https://notexai.pro/login.html> and request a free API key. We have a free tier for testing, and then a pay-as-you-go tier for production. You can read more about Authentication and error codes in the Authentication page.

​ Available endpoints With your API key, you can either use the REST API or our Python SDK to start building your own web agent or automations on top of NotexAI. The API has 3 major endpoints:

* **POST /observe**: Observes a website and extracts action space and controls
* **POST /step**: Acts on a website you observed and performs an action
* **POST /scrape**: Scrapes a website and extracts structured data

You can read more about these endpoints in the API Documentation.

​ Opensource If you’re willing to contribute to the project or want to deploy your own NotexAI infrastructure at home, you’re free to do so. We’ve open-sourced the core of the service on GitHub under an Apache 2.0 license.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://notexai.gitbook.io/notexai/quickstart.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
