Awesome AI Agents › Web Agents
AgentLab is an open-source framework designed for developing, testing, and benchmarking web agents across a variety of tasks. It emphasizes scalability and reproducibility, providing a unified platform to accelerate research in web agent development. The framework supports large-scale parallel experiments using Ray, enabling efficient execution of numerous agent tasks simultaneously. AgentLab integrates with BrowserGym, a platform that hosts multiple benchmarks such as WebArena, WorkArena, WebLinx, VisualWebArena, AssistantBench, GAIA, Mind2Web-live, and MiniWoB, covering a wide range of web interaction challenges. It offers a unified API for large language models (LLMs) including OpenRouter, OpenAI, Azure, and self-hosted models via TGI, facilitating seamless integration of AI agents. The framework includes features for reproducibility, ensuring that experiments can be reliably repeated and verified. AgentLab also provides a leaderboard system hosted on Hugging Face Spaces to track and compare agent performance on supported benchmarks. The setup requires Python 3.11 or 3.12 and Playwright for browser automation. Users can launch experiments programmatically or via a command-line interface, with support for debugging and handling job timeouts to manage complex web interactions. The framework is not intended as a consumer product but as a research tool to foster advancements in web agent technology. It supports multi-tab browsing, task diversity, and various hosting methods for benchmarks, including self-hosted Docker instances and live web environments. Overall, AgentLab is a comprehensive, extensible, and easy-to-use platform for advancing the state of web agent research and benchmarking.
https://github.com/ServiceNow/AgentLab
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.
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.