tinyfish-io/agentql

AgentQL is a suite of tools for connecting your AI to the web. Featuring a query language and Playwright integrations for interacting with elements and extracting data quickly, precisely, and at scale. Includes REST API, Python and JavaScript SDKs, browser debugger.

What it solves

AgentQL addresses the fragility and complexity of web scraping and browser automation. Traditional methods rely on rigid selectors (like CSS or XPath) that break whenever a website updates its UI. AgentQL allows users to extract data and automate workflows using natural language, making scripts resilient to UI changes and capable of working across similar websites.

How it works

It provides an AI-powered query language that uses natural language selectors to pinpoint elements and data on any web page, including those that are dynamically generated or behind authentication. The system translates these intuitive queries into structured data outputs. It integrates with Playwright via Python and JavaScript SDKs, offers a REST API for direct execution, and includes a browser-based debugger for real-time query refinement.

Who it’s for

It is designed for developers building AI agents, data engineers performing web scraping, and QA engineers creating automated tests who need a more flexible and maintainable way to interact with live websites.

Highlights

  • Self-healing selectors: Queries remain functional even when the website's underlying HTML structure changes.
  • Cross-site compatibility: The same natural language query can often be used across different websites with similar content.
  • Structured output: Users can define the exact shape of the data they want to extract directly within the query.
  • Broad accessibility: Works on public and private pages, including those requiring authentication.
  • Comprehensive tooling: Includes SDKs for Python and JS, a REST API, and a dedicated debugger extension.

Related

  • Project
    0xMassi/webclaw

    A web extraction tool that converts websites into clean Markdown, JSON, and LLM-optimized context for AI agents and RAG pipelines.

  • Dispatch
    Introducing agent-qa: An Open-Source Agentic QA Harness with Execution Memory

    Explore agent-qa, an open-source framework that allows developers to write QA tests in natural language and uses execution memory to reduce flakiness and accelerate test runs.

  • Project
    platonai/Browser4

    Browser4 is an AI‑native browser automation platform. It offers a Rust‑based backend and a human‑friendly CLI (`browser4‑cli`) that lets humans or LLM‑driven agents open real Chromium sessions, interact with pages (click, fill, wait, etc.), and extract data via deterministic X‑SQL/CSS selectors or LLM‑assisted commands. It supports zero‑token, ML‑based spreadsheet generation (WebMiner), high‑throughput swarm crawling, and an extensible plugin/skill system, making it suitable for large‑scale web automation and autonomous agents.

  • Project
    vostride/agent-qa

    An agentic QA harness that allows users to write web and mobile tests in natural language and uses self-healing AI agents to adapt to UI changes.

  • Project
    any4ai/AnyCrawl

    A high-performance crawling and scraping toolkit that provides SERP, site crawling, and LLM-powered structured data extraction for AI applications.