Awesome AI Agents › Web Agents
The project "awesome-web-agents" by steel-dev is a curated list of tools, frameworks, and resources dedicated to building AI web agents that can autonomously browse and interact with the web. It serves as a comprehensive directory for developers and researchers interested in AI agents capable of web navigation, automation, and interaction. The repository categorizes various AI web agents, including autonomous web agents that navigate the web through user-friendly interfaces, computer-use agents that control browsers and computers, AI web automation tools that translate natural language instructions into web interactions, AI web scrapers and crawlers, web search and query tools, benchmarks and research, tutorials, and guides. The project highlights notable AI agents and frameworks such as Surf.new, OpenAI Operator, Browser-Use, Skyvern-AI, Proxy by Convergence, Google Project Mariner, Runner H, WebVoyager, AgentGPT, Agent-E, Kura, Manus, doBrowser, WebSurfer, Magentic-One, Harpa.ai, Yutori, Automina, rtrvr.ai, and Nanobrowser. These agents offer functionalities ranging from autonomous web browsing, task automation, multi-agent systems, to natural language control of browsers. Additionally, the list includes computer-use agents like Anthropic Computer Use, Self-Operating Computer Framework, Highlight, OpenInterpreter, and UI-TARS, which enable AI models to interact with desktop environments and GUIs. The repository also features AI web automation tools such as Asteroid.ai, PulsarRPA, VimGPT, and Cekura.io, which facilitate browser automation and data extraction through AI. The project is closely linked to Steel, an open-source browser API designed specifically for AI agents, making it easier to build AI applications that interact effectively with the web. The repository encourages community engagement through Discord and provides resources for those interested in implementing Steel. Overall, this project is a valuable resource for anyone looking to explore or develop AI-driven web agents and automation tools.
https://github.com/steel-dev/awesome-web-agents
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.
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.