AI web scraping agent

LLM-driven web scraping API that turns natural-language prompts into structured JSON.

Source-available workflow automation with first-class AI-agent and RAG building blocks.

AI browser agent that automates web workflows from natural-language instructions, with CAPTCHA and 2FA handling built in.

Open-source browser automation harness and cloud platform for LLM agents that drive real websites.

Open-source visual workspace for building, deploying, and monitoring AI agents.

Web search API built for AI agents, with structured outputs and token-efficient highlights.

Web scraping and crawling API that returns LLM-ready markdown, JSON, or structured data from any URL.

Generalist agent for research, code, and web tasks.

Open-source bridge that hands your already-logged-in Chrome session to a CLI and AI agents.

Minimal open-source deep-research agent that iteratively searches, scrapes, and reasons to produce cited markdown reports.

Cloud browser infrastructure built for AI agents that need to scrape, click, and navigate the live web.

An in-page JavaScript GUI agent that drives web interfaces with natural language, no headless browser required.

Open-source local-first AI agent that browses the web, writes code, and runs tasks without sending anything to the cloud.

Gradio web UI for running browser-use AI agents in a real or persistent Chrome session.

Web search and research APIs purpose-built for LLMs and AI agents.

Plain-English workflow automation that generates and runs cloud code from your prompt.

Headless browser infrastructure for AI agents

An AI-native browser from The Browser Company that turns tabs into an agentic assistant for knowledge workers.

MCP server that gives Claude and other LLMs DuckDuckGo web search plus URL content fetching, with no API key required.

Web search, code search, and company research for AI assistants over MCP

The world's first agentic browser that plans and executes multi-step web workflows for you.

MCP server that gives Claude, Cursor, and other AI agents native web scrape, crawl, search, and extract tools via Firecrawl.

Official Kagi Search MCP server: search and extract the web from any MCP-compatible agent.

Official Model Context Protocol reference server that lets any MCP-compatible LLM fetch web pages and read them as clean markdown.

An agentic browser from Opera built to act on the web, not just render it.

An agentic AI browser from Perplexity that reads, reasons over, and acts on the pages you're viewing.

Official MCP server for Perplexity's Sonar search, research, and reasoning APIs

Microsoft's official Model Context Protocol server for browser automation via Playwright.

Reference MCP server that lets LLMs drive a real Chromium browser via Puppeteer.

Adaptive Python web-scraping framework with a built-in MCP server for AI coding agents.

The SDK for browser agents

One secure API for real-time web access for AI agents