Awesome AI AgentsBrowser Automation Tools

hyperbrowserai/HyperAgent

⭐ 1564 TypeScript added to this list on 2025-05-02 repository created 2025-04-14

HyperAgent is an advanced AI-powered browser automation tool that enhances the Playwright framework by integrating large language models (LLMs) to enable natural language commands for web automation tasks. It eliminates the need for brittle scripting by allowing users to interact with web pages using simple, intuitive AI commands such as `page.ai()`, `page.extract()`, and `executeTask()`. This makes it easier to automate complex browsing tasks like data extraction, navigation, and interaction with web elements without deep programming knowledge. The project supports fallback to regular Playwright commands when AI is not required, ensuring flexibility and robustness. It includes stealth mode features to avoid detection by anti-bot systems, making it suitable for web scraping and automation in environments with bot protection. HyperAgent is cloud-ready and can scale to hundreds of browser sessions using the Hyperbrowser platform, which provides scalable headless browser infrastructure. HyperAgent also supports integration with external tools through its MCP client, enabling workflows such as writing extracted web data directly to Google Sheets. It offers multi-page management, allowing users to create and control multiple browser pages simultaneously and execute tasks on specific pages. Customization is a key feature, with support for defining output schemas using the Zod library to structure extracted data precisely. The tool is compatible with multiple LLM providers, including OpenAI's GPT models and Anthropic's Claude, allowing users to choose their preferred AI backend. Developers can extend HyperAgent's functionality by creating custom actions with defined parameters and execution logic, enhancing its adaptability to various automation scenarios. The project provides a command-line interface (CLI) for quick task execution and debugging, as well as a comprehensive library for programmatic use. Overall, HyperAgent is designed to simplify and supercharge browser automation by leveraging AI, making it accessible, scalable, and highly customizable for diverse automation needs.

https://github.com/hyperbrowserai/HyperAgent

agentaiai-browser-automationanthropicautomationautomation-workflowschromeclicloud-scalingcustom-actionsgoogle-sheets-integrationheadless-browsershyperbrowserlarge-language-modelsllmmcp-clientmulti-page-managementnatural-language-commandsopenaioutput-schemaplaywrightstealth-modewebweb-scrapingzod

Also in Browser Automation Tools

browser-use/browser-use

Browser-use is a project that enables AI agents to control and automate web browsers, allowing users to perform complex tasks through natural language commands and AI-driven browser interactions.

CloakHQ/CloakBrowser

CloakBrowser provides a stealthy Chromium binary with C++ source-level fingerprint patches to pass bot detection, serving as a drop-in Playwright/Puppeteer replacement.

jackwener/OpenCLI

OpenCLI converts any website or local tool into a command-line interface, enabling both human interaction and AI agent automation through logged-in browser sessions.

browserbase/stagehand

Stagehand is a production-ready AI web browsing framework that combines code and natural language to enable reliable and extensible browser automation.

browser-use/web-ui

A web-based user interface, powered by Gradio, for interacting with browser automation agents, supporting various LLMs and custom browser configurations.

citrolabs/ego-lite

ego lite is a specialized browser designed for AI agents to perform web automation in parallel with human browsing, offering isolated workspaces and enhanced page snapshots.

jo-inc/camofox-browser

Camofox-browser is a stealth headless browser server, powered by Camoufox (a Firefox fork), designed for AI agents to bypass bot detection and Cloudflare, offering a Puppeteer/Playwright alternative.

microsoft/fara

Fara-7B is a compact and efficient agentic small language model by Microsoft designed to perform multi-step computer tasks through visual interaction, achieving state-of-the-art performance on web automation benchmarks while enabling on-device deployment for privacy and low latency.