agentql

Overview of agentql

What it is

AgentQL is a suite of tools for extracting data and automating workflows on live web sites. It features an AI-powered query language, Python and JavaScript SDKs, a browser-based debugger, and a REST API endpoint. It uses natural language queries to pinpoint data and elements on any web page, including authenticated and dynamically generated content. Users can define structured data output and apply transforms within queries. The natural language selectors find elements based on page content and work across similar web sites, self-healing as UI changes over time.

Key features

• Playwright integration: AgentQL's Python and JavaScript SDKs integrate with Playwright for automation and testing.
• Cross-site compatibility: The same query can be used across different sites with similar content.
• Structured output: The shape of the query defines the output structure.
• Natural language selectors: Find elements and data using intuitive queries.
• Transforms and extracts: Data can be transformed and extracted within queries.
• Works on any page: Public or private, any site, any URL, even behind authentication.
• Resilience to UI changes: Queries work regardless of page structure changes over time.

Use cases

AgentQL can be used for a variety of web automation and data extraction tasks. Examples from the repository include getting started scripts, closing cookie dialogs, comparing product prices, infinite scrolling, site login, headless browser usage, e-commerce pricing data extraction, sentiment analysis, collecting paginated data from HackerNews, scraping Google Maps to CSV, and more.

Getting started

See the repository README for installation and quick start instructions.

License and pricing

AgentQL is open source under the MIT license.

Based on the project's public README and repository metadata.