Awesome AI Agents › Web Agents
WebShop is a sophisticated simulated e-commerce environment designed to facilitate research in grounded language agents and scalable real-world web interaction. It features a vast dataset comprising 1.18 million real-world products and over 12,000 crowd-sourced text instructions, challenging agents to navigate diverse webpages and perform complex actions such as searching, customizing, and purchasing products based on natural language instructions. The environment tests agents' abilities in understanding compositional instructions, reformulating queries, handling noisy webpage text, and strategic exploration. WebShop supports two modes: an HTML mode that renders a full webpage environment and a simpler text-based mode compatible with OpenAI gym, enabling flexible agent training and evaluation. The project includes baseline models employing rule-based, imitation learning, and reinforcement learning approaches, and supports sim-to-real transfer to other environments. It provides comprehensive setup instructions, including dependencies like Python 3.8, Java, and optional image feature files for enhanced model capabilities. The repository also offers a Hugging Face demo for interactive querying and product search on platforms like Amazon and eBay. WebShop is a valuable resource for advancing research in natural language processing, reinforcement learning, and web interaction, promoting the development of intelligent agents capable of complex, real-world tasks in e-commerce settings. The project encourages community contributions and is well-documented with examples, making it accessible for researchers and developers interested in grounded language understanding and agent-based web navigation.
https://github.com/princeton-nlp/WebShop
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.
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.