Awesome AI Agents › Web Agents
Index is a state-of-the-art open-source browser agent designed to autonomously perform complex tasks on the web. It leverages advanced AI models, currently powered by Claude 3.7 Sonnet with extended thinking capabilities, and plans to support additional models in the future. The project offers multiple ways to interact with the agent, including a hosted API, a hosted user interface, and options for self-hosting the UI. This flexibility allows users to integrate the agent into various workflows and environments. The core functionality of Index revolves around automating web browsing tasks such as navigating websites, extracting information, summarizing content, and even creating spreadsheets based on gathered data. For example, users can instruct the agent to visit a site like Y Combinator, summarize the top companies in a batch, and organize the information into a Google Sheets document. Index also emphasizes observability and monitoring through integration with the Laminar platform, which provides advanced browser agent observability features. This includes tracing the agent's actions and recording browser sessions, enabling users to gain insights into the agent's behavior and performance. The project supports easy installation and setup, with dependencies managed via Python's package manager and browser automation facilitated by Playwright. It provides example code snippets for running the agent locally, streaming output, connecting to remote browser sessions via Chrome DevTools Protocol, and customizing browser window sizes. Overall, Index is a powerful tool for AI-driven browser automation, suitable for developers and organizations looking to automate complex web tasks with high observability and flexibility. It is backed by the Laminar team and supported by a vibrant community with resources such as Discord and social media channels.
https://github.com/lmnr-ai/index
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.
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.
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.