Anchor Browser delivers a state-of-the-art 89% Score on the industry-standard benchmark WebVoyager, leveraging browser-use as a core component of the automation capability.
Anchor Browser provides within its SDK the agent.task method that enables natural language control over web browsing sessions. This capability allows you to automate complex web tasks without coding the whole flow.
import Anchorbrowser from 'anchorbrowser';(async () => { const anchorClient = new Anchorbrowser({ apiKey: process.env.ANCHORBROWSER_API_KEY }); const response = await anchorClient.agent.task( 'Extract the main heading', // Required { taskOptions: { url: 'https://example.com', // Either sessionId or url is required humanIntervention: true, // Allow human intervention during task execution detectElements: true, // Improves the agent's ability to identify and interact with UI elements maxSteps: 40, // Maximum number of steps the agent can take agent: 'browser-use', // browser-use (default), openai-cua, or gemini-computer-use provider: 'groq', // For browser-use agent only, openai, gemini, groq, azure, xai model: 'openai/gpt-oss-120b', // For browser-use agent only, see model list below extendedSystemMessage: 'Focus on extracting the main heading from the page', secretValues: { // Secret values to pass to the agent for secure credential handling API_KEY: 'your-secret-key' } } } ); console.log(response);})();
The AI object can also be used to extract structured data from the browser. This is done by providing a JSON schema to the AI object, which will then return the structured data.
The following demonstrates using Zod and Pydantic to utilize the structured output capability.
Copy
Ask AI
// Create a browser session and get referencesconst browser = await anchorClient.browser.create();const context = browser.contexts()[0];const page = context.pages()[0];const ai = context.serviceWorkers()[0]; // Get the AI service worker// Define the expected output structure using Zod schemaconst outputSchema = z.object({ nodes_cpu_usage: z.array( z.object({ node: z.string(), // Node name cluster: z.string(), // Cluster identifier cpu_avg_percentage: z.number(), // CPU usage percentage }) )});// Create task payload with structured output schemaconst taskPayload = { output_schema: z.toJSONSchema(outputSchema);, // Define expected output structure prompt: 'Collect the node names and their CPU average %',};// Navigate to the target pageawait page.goto("https://play.grafana.org/a/grafana-k8s-app/navigation/nodes?from=now-1h&to=now&refresh=1m");// Execute the AI task with structured outputconst result = await ai.evaluate(JSON.stringify(taskPayload));console.info(result);// Clean up browser resourcesawait browser.close();
Anchor Browser comes with an embedded AI component, that allows to control the browser or extract data using natural language. This capability allows to use the browser without any coding.
import Anchorbrowser from "anchorbrowser";(async () => { const anchor_client = new Anchorbrowser({apiKey: process.env.ANCHORBROWSER_API_KEY}); // Create a browser session const browser = await anchor_client.browser.create(); const page = browser.contexts()[0].pages()[0]; // Get the AI service worker const ai = context.serviceWorkers().find(sw => sw.url().includes('chrome-extension://bppehibnhionalpjigdjdilknbljaeai/background.js') ); await page.goto("http://docs.anchorbrowser.io/", {waitUntil:'domcontentloaded'}); // Use the embedded 'ai' object const result = await ai.evaluate('Find the last game played by Milwaukee in the NBA and return the result'); await browser.close(); console.log(result);})();
Securely pass credentials and sensitive data to AI agents during task execution. Secret values are not logged and automatically cleaned up after completion.
