Awesome AI Agents › Web Agents
invisible_playwright_mcp is a browser automation agent built on Playwright whose stated goal is to complete browsing tasks without triggering the anti-bot defenses and captchas that typically stop other AI browser agents. It can be used in two ways. First, as an MCP server installed into an AI coding or chat assistant (the README documents installation for Claude Code, Codex and Gemini CLI through their respective plugin or extension mechanisms), so the assistant gains a browsing tool it can call mid-conversation. Second, as a standalone local web application: the user supplies an OpenRouter API key, runs the tool with a `ui` subcommand, and gets a two-pane interface with a chat panel on one side and a live view of the controlled browser on the other, so the same natural-language instructions drive real web automation without any separate IDE. Installation on both Windows and Linux relies on the `uv` Python tool installer, after which the package is run directly with `uvx`. The intended use cases are tasks that need an actual browser session and human-like judgment about page content, rather than a structured API: filling forms, navigating multi-step flows, or extracting information from sites that resist scripted access. The project frames itself against other web-browsing agents by emphasizing that its automation footprint is harder for anti-bot systems to distinguish from a real user, which is also reflected in its name and README imagery. It is written in Python and distributed for direct installation into MCP-capable assistants or as a self-contained UI, positioning it as infrastructure other agents call rather than an end-user product on its own.
https://github.com/feder-cr/invisible_playwright_mcp
LaVague is an open-source Large Action Model framework for developing AI Web Agents that automate web-based tasks using components like a World Model and Action Engine with support for Selenium, Playwright, and Chrome extension drivers.
Index is an advanced open-source browser agent that autonomously performs complex web tasks using AI models, offering hosted and self-hosted options with strong observability features.
Tarsier is a vision utility that enhances web interaction agents by tagging webpage elements and converting screenshots into text representations to enable effective LLM-based web automation.
A curated list of tools, frameworks, and resources for building AI web agents that autonomously browse and interact with the web.
WebVoyager is an end-to-end web agent powered by Large Multimodal Models that interacts with real-world websites to complete diverse user tasks using textual and visual information.
Python SDK for the Oxylabs AI Studio scrape agent, which extracts data from a single web page using a natural language prompt and returns structured JSON or Markdown without CSS or XPath selectors.
AgentLab is an open-source framework for developing, testing, and benchmarking scalable and reproducible web agents across diverse tasks using BrowserGym benchmarks and large-scale parallel experiments.
WebShop is a simulated e-commerce environment designed to train and evaluate grounded language agents for complex real-world web interaction tasks involving product search and purchase based on natural language instructions.