Awesome AI Agents › Web Agents
WebVoyager is a cutting-edge project that develops an end-to-end web agent powered by Large Multimodal Models (LMMs) capable of interacting with real-world websites to complete user instructions. The project integrates both textual and visual information to perform diverse web tasks, making it a generalist web navigation and interaction tool. It leverages an online web browsing environment built with Selenium, allowing the agent to operate in real-time on actual websites. The repository includes a comprehensive dataset of 643 task queries across 15 popular websites, with tasks ranging from booking flights to searching for information, and also incorporates tasks from the GAIA benchmark dataset. The project supports task expansion using GPT-4 to generate new diverse web tasks, enhancing the agent's capabilities and adaptability. WebVoyager provides an automated evaluation protocol using GPT-4V to assess the agent's performance on these tasks. The environment setup requires Python 3.10, Selenium, and Chrome or Chromium browsers, with detailed instructions for installation and running the agent. Users can run the agent with customizable parameters such as maximum iterations, temperature for model diversity, and options for headless browsing or text-only modes. The project also includes tools for prompt optimization to improve agent performance. Overall, WebVoyager represents a significant advancement in autonomous web agents by combining multimodal understanding with practical web interaction capabilities, making it useful for research and development in AI-driven web automation and assistance.
https://github.com/MinorJerry/WebVoyager
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.
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.
Ash Agents is a Python swarm framework that performs web tasks through disposable agents: each runs in an isolated browser context with its own fingerprint and egress, then is destroyed so no interaction links back to the user.