Awesome AI Agents › Web Agents
Open-CUAK (Open Computer Use Agent Kit) is an open-source platform designed to teach, hire, and manage automation agents at scale, with a primary focus on browser automation. The project aims to provide a reliable and scalable solution for businesses to automate workflows, ensuring high reliability and productivity. Open-CUAK is positioned as a free alternative to OpenAI Operator, emphasizing privacy, flexibility, and the ability to run thousands of automation agents simultaneously. The platform supports vision-based automation that mimics human interaction, enabling it to bypass bot detection and handle complex tasks with ease. It includes features such as turning any browser into an Operator companion via a browser extension, using dedicated remote browsers to mitigate security risks, and managing cookies for seamless login experiences. Open-CUAK is compatible with various vision-compatible AI models, including frontier and open-source models like Claude, Gemini, and LLaVA. The project is still in early development but aims to introduce SOP-based training for agents, centralized account management, task monitoring, and scalability to deploy hundreds of agents in parallel. The platform can be run locally to ensure full privacy and control over automation workflows. It offers demos showcasing automation agents performing tasks such as creating posters on Canva and searching for flights on Expedia. The development setup includes instructions for installing dependencies, running development servers, and building production versions using Docker. Open-CUAK is developed and maintained by the Aident AI team and is intended to democratize automation by making it accessible and reliable for real-world business applications, promoting abundant and equally distributed productivity.
https://github.com/Aident-AI/open-cuak
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.