lmnr-ai/index
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.
Awesome AI Agents › Web Agents
lavague-ai/LaVague
LaVague is an open-source Large Action Model framework designed to help developers create AI Web Agents that automate web-based processes for end users. The framework enables agents to take a high-level objective, such as retrieving installation steps for a software library, and generate the necessary actions to fulfill that objective on the web. The core components of LaVague include a World Model that interprets the objective and current web page state to produce instructions, and an Action Engine that compiles and executes these instructions using web automation tools like Selenium or Playwright. LaVague also offers a specialized tool called LaVague QA, built on the same framework, which is tailored for QA engineers to automate test writing by converting Gherkin specifications into executable tests, significantly improving web testing efficiency. The framework supports multiple web drivers including Selenium, Playwright, and a Chrome extension, each with varying levels of feature support such as handling iframes, multiple tabs, and element highlighting. The project provides extensive documentation, demos, and examples to help users get started quickly, including a Google Colab notebook and a Gradio interface for interactive use. It includes features like built-in contexts for configuration, a test runner for benchmarking, token counting tools for cost estimation, logging, debugging tools, and a Chrome extension for enhanced functionality. LaVague is community-driven with a clear contribution process and active support channels including Discord and GitHub issues. It leverages large language models, primarily OpenAI's GPT-4, to interpret and execute web automation tasks, with customizable model options. The project also addresses cost considerations related to LLM usage and provides tools to monitor token consumption and estimate expenses. Overall, LaVague is a comprehensive framework aimed at simplifying the development of intelligent web automation agents that can perform complex tasks autonomously, making it valuable for developers and QA engineers looking to enhance productivity through AI-driven web interactions.
https://github.com/lavague-ai/LaVague
Also in Web Agents
reworkd/tarsier
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.
steel-dev/awesome-web-agents
A curated list of tools, frameworks, and resources for building AI web agents that autonomously browse and interact with the web.
MinorJerry/WebVoyager
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.
oxylabs/ai-scraper-py
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.
ServiceNow/AgentLab
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.
princeton-nlp/WebShop
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.
EthanXiang777/ash-agents
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.