AgentQL

Product Hunt#1 Product of the DayProduct Hunt#1 Product of the WeekMake the web AI‑readyAgentQL connects LLMs and AI agents to the entire webGet startedSign upAgentQL queryCopy code{ jobs(only in Netherlands)[] }JSON{ "jobs": [ "Web Developer", "Data Engineer", "Sheep wrangler", "Graphic designer", "Product manager", "Frontend developer", "Backend developer" ] }See all examplesIntegrationsPlays well with othersDiscover how AgentQL integrations can elevate your projects. Explore the documentation or contact us to learn more.Add AgentQL to your workflowAgentQL is a suite of tools for connecting your AI to the webFeaturing a query language and parser for interacting with elements and extracting data quickly, precisely, and at scale.Versatile SDKInteract with web page elements via Playwright and our Python and JavaScript SDKs and headless browsers.Browser-based debuggerUse the debugging browser extension for optimizing queries in real time on any web page.RobustnessA robust alternative to fragile XPath and DOM/CSS selectors: AgentQL uses AI to analyze the page’s structure to find the data you’re looking for. See how it works.XPathCSS/html/body/div[1]/div[1]/div[2]/div[1]/div[1]/div/div[2]/div[2]/div[1]/a/div[1]/img /html/body/div[1]/div[1]/div[2]/div[1]/div[1]/div/div[2]/div[2]/div[1]/a/div[1]/span /html/body/div[1]/div[1]/div[2]/div[1]/div[1]/div/div[2]/div[2]/div[1]/a/div[2]/spanAgentQL queryCopy code{ results { products[] { product_image product_name prouct_price(include currency symbol) } } }BrowserlessUse our REST API to retrieve public facing data from any URL, no browser required.PDF parsingParses difficult information like tables from PDFs. Try it on the playground.Your perfect partner in data workflows and simple automationWorks on any pagePublic or private, any site, any URL, even behind authentication.Structured dataDefine the shape of your data with your query.Self-healingGet consistent results despite dynamic content and page changes.Reusable codeThe same query works across multiple similar pages.Stop wasting time writing fragile parsing scripts and crunching reams of HTML to find what you needAgentQL queryCopy code{ product_name product_price(include currency symbol) }JSON{ "product_name": "Qwilfish", "product_price": "$77.00" }Choose your planTry out AgentQL for free, no credit card requiredSign up for free trialExplore Playground300 free API calls i10 API calls per minute 1 hr of remote browser i1 concurrent remote browser session iCommunity and email support iFull access to developer tools iSign up for free trialExplore PlaygroundExplore all plansStarter$0/monthlyPerfect for developers building web agents and data workflows.Sign up with Starter50 free API calls/monthi$0.02 per API call after the initial limit10 API calls per minute10 hrs of remote browser includedi$0.12/hr of remote browser time5 concurrent remote browser sessionsCommunity and email supportiFull access to developer toolsiProfessionalMost Popular$99/monthlyFor teams running regular data workflows and web automation pipelines.Sign up with Professional10,000 API calls/month includedi$0.015 per API call after the initial limit50 API calls per minute500 hrs of remote browser includedi$0.10/hr of remote browser time100 concurrent remote browser sessionsPriority email supportCommunity supportiFull access to developer toolsiEnterpriseCustomFully managed solutions for accessing data from websites and documents.Let’s chat!Fastest time to marketReady-to-use datasetsFully managed dedicated cloud environmentOn-premise deployment available24/7 premium supportDedicated account managerJoin the thousands of developers using AgentQL's powerful tools as part of their data workflows“If we were to do text based grounding with raw HTML content, we would often hit context window issues and hallucinations. With AgentQL sending the query and getting the results is a gamechanger for text grounding.”Vladimir de TurckheimFounderHeal.dev“AgentQL handles web automation painlessly, which is quite unusual. It's awesome stuff — very easy to use and with very well-written responses. The effort to differentiate from competitors through semantic search is very palpable.”Fahd MirzaAI YouTuber, Lead AI Engineer@fahdmirza“Love the fact that we can describe the elements that we can work with, or we can just give a prompt and AgentQL will go to the websites and define the elements that it will have to deal with.”Reda MarzoukAI/RPA Senior Developer@redamarzouk“AgentQL has been a game-changer in my data extraction process! The ability to create reusable configurations across similar website layouts has saved me considerable time and effort”Mahmoud MasmoudiData EngineerHoveGet startedHolds no opinions on what’s and how’s. Build whatever makes sense to you.See samples on GitHubRead the docs × We use third-party cookies in order to personalize your site experience.Press again to continue 0/1CustomizeReject AllAccept all --- AgentQL - PricingChoose your planTry out AgentQL for free, no credit card requiredSign up for free trialExplore Playground300 free API calls i10 API calls per minute 1 hr of remote browser i1 concurrent remote browser session iCommunity and email support iFull access to developer tools iSign up for free trialExplore PlaygroundExplore all plansStarter$0/monthlyPerfect for developers building web agents and data workflows.Sign up with Starter50 free API calls/monthi$0.02 per API call after the initial limit10 API calls per minute10 hrs of remote browser includedi$0.12/hr of remote browser time5 concurrent remote browser sessionsCommunity and email supportiFull access to developer toolsiProfessionalMost Popular$99/monthlyFor teams running regular data workflows and web automation pipelines.Sign up with Professional10,000 API calls/month includedi$0.015 per API call after the initial limit50 API calls per minute500 hrs of remote browser includedi$0.10/hr of remote browser time100 concurrent remote browser sessionsPriority email supportCommunity supportiFull access to developer toolsiEnterpriseCustomFully managed solutions for accessing data from websites and documents.Let’s chat!Fastest time to marketReady-to-use datasetsFully managed dedicated cloud environmentOn-premise deployment available24/7 premium supportDedicated account managerStart your journey with AgentQLDiscover how easy it is to integrate advanced AI features and enhance your business operations effortlessly.Get startedExplore the docs × We use third-party cookies in order to personalize your site experience.Press again to continue 0/1CustomizeReject AllAccept allFeedbackHow would you rate your experience?HateLoveNext --- SearchKAgentQL DocumentationGet started Quick Start GuideGet up and running with AgentQL's tools and query language in less than 5 minutes.APIs and SDKsAgentQL has a REST API for data extraction and Python and JavaScript SDKs that use Playwright for data extraction and automation.IntegrationsUse AgentQL with your favorite Agentic frameworks, low-code platforms, and automation tools. How to get things done with AgentQL Check out our extensive guides to learn how to use AgentQL to automate web interactions and extract data from web pages. Automate web interactionsAgentQL's SDK is integrated with Playwright, which allows you to programmatically interact with web sites.Extract dataYou can use AgentQL's SDKs and REST API endpoint to retrieve data from any web page. Dive deeper ExamplesExplore our collection of example scripts to get started with AgentQL.GuidesFind detailed guides on how to use AgentQL's tools and query language to automate web interactions and extract data from web pages.ToolsOur Python and JavaScript SDKs, Debugging Extension, and REST API support how you want to work.ConceptsLearn about the core concepts of the AgentQL query langauge and how it works under the hood. Need help? TroubleshootingGot stuck? Find solutions to common issues in our FAQ.SupportOur team is here to help you with any questions you have. Get in touch!FeedbackHow would you rate your experience?HateLoveNext --- SearchKAgentQL Quick StartThis guide shows you how to get started interacting with elements and extracting data from web pages using AgentQL queries. You will learn how to use the Chrome extension for debugging and how to implement queries using AgentQL's Python SDK. What's an AgentQL query? AgentQL is a query language and a set of supporting developer tools designed to identify web elements and their data using natural language and return them in the shape you define. Here is an AgentQL query you can use right now to locate the search button on this page: { search_button }Copy code This query can return each heading on this page: { headings[] }Copy code The following shows you how to execute queries to retrieve data and elements from web pages starting right here, with the page you are on now. Get your API key You need an API key to make AgentQL queries. Get a free API key on the AgentQL Developer Portal, and you'll be ready to go! Query this page with the AgentQL Debugger Chrome extension The AgentQL Debugger lets you write and test queries in real-time on web pages, without needing to spin up the Python SDK. It's perfect for debugging queries before putting them into production! Here's how to get started: Install the AgentQL Debugger from the Chrome Web Store. Come back to this page and open Chrome DevTools (Ctrl+Shift+I on Windows/Linux or Cmd+Opt+I on Mac). In the top bar of the devtools panel, select "AgentQL." noteIf you don't see the option, click the overflow menu button (») and select "AgentQL" from the list. Enter your API key when prompted. In the query panel, try this query: { search_button }Copy code Click "Fetch Web Elements" to run the query to return the search button element. Look under the AgentQL tab to find an entry for the search button. Hovering over the entry highlights its element on the page. Try it out The best way to learn how AgentQL works is to play around with it in the extension. Here are some things you can try: Click the eye icon to navigate to the element on the page. Click </> to navigate to the element in the devtools. Click "Fetch Data" to return the contents of the queried elements instead of the elements themselves (great for scraping). Use [] to return a list of items. Use () to add additional context to find the exact element: { headings(all the headings inside the article)[] }Copy code Experiment with different queries to get a feel for how AgentQL works. For example, try this one out with "Fetch Data" to get a list of all the headings on this page: { headings[] }Copy code You can even nest items: { breadcrumbs { first_item last_item } }Copy code Perform the query with the AgentQL SDK Now that you're familiar with writing queries, you can use the SDK to run the same query programmatically. noteIf you use virtual environments, we recommend using one for the following steps. In your project folder, install the AgentQL SDK and initialize AgentQL: terminalpip3 install agentql agentql initCopy code Provide your API key. Create a new Python file, example_script.py. Add the following code: In your project folder, install the AgentQL SDK and CLI: terminalnpm install agentql npm install -g agentql-cliCopy code Install dependencies by running the following command: terminalagentql initCopy code Set the AGENTQL_API_KEY environment variable with your API key. To set the environment variable temporarily for your terminal session, in your terminal runterminalexport AGENTQL_API_KEY=your-api-keyCopy code Create a new JavaScript file, example_script.js. Add the following code: PythonJavaScriptexample_script.jsjsconst { wrap, configure } = require('agentql'); const { chromium } = require('playwright'); configure({ apiKey: process.env.AGENTQL_API_KEY }); async function main() { const browser = await chromium.launch({headless: false}); const page = await wrap(await browser.newPage()); await page.goto('https://docs.agentql.com/quick-start'); // Find "Search" button using Smart Locator const searchButton = await page.getByPrompt('search button'); // Interact with the button await searchButton.click(); // Define a query for modal dialog's search input const SEARCH_BOX_QUERY = ` { modal { search_box } } ` // Get the modal's search input and fill it with "Quick Start" let response = await page.queryElements(SEARCH_BOX_QUERY); await response.modal.search_box.fill("Quick Start"); // Define a query for the search results const SEARCH_RESULTS_QUERY = ` { modal { search_box search_results { items[] } } } ` // Execute the query after the results have returned then click on the first one response = await page.queryElements(SEARCH_RESULTS_QUERY); await response.modal.search_results.items[0].click(); // Used only for demo purposes. It allows you to see the effect of the script. await page.waitForTimeout(10000); await browser.close(); } main();Copy code Run the script: terminalpython3 example_script.pyCopy code terminalnode example_script.jsCopy code This script opens this site, docs.agentql.com, clicks the search button, fills in the search modal's input with "Quick Start," and clicks the first result—bringing you back to this page. Next steps Congratulations! You've now used AgentQL queries both in the Chrome extension and the SDK. This is the AgentQL workflow: optimizing and debugging queries with the extension before running them in the SDK. Here are some next steps to explore: Learn more about AgentQL query syntax Explore best practices for writing queries Check out an example script for collecting YouTube comment data Happy querying with AgentQL!FeedbackHow would you rate your experience?HateLoveNext