awesome-web-agents
🔥 A list of tools, frameworks, and resources for building AI web agents
https://github.com/steel-dev/awesome-web-agents
Last synced: 4 days ago
JSON representation
-
Autonomous Web Agents
-
- Runner H - Runner H is a state-of-the-art AI agent that will allow anyone to automate complex, cumbersome, multi-step tasks without repetitive and manual input.
- Surf.new - An open-source playground for chatting with different web agents. 
- OpenAI Operator - OpenAI's AI agents that can browser the web for you.
- Skyvern-AI - Framework to automate browser-based workflows. 
- Proxy by Convergence - Proxy is your AI-powered digital assistant that explores the web and executes tasks through simple conversation.
- Google Project Mariner - A research prototype exploring the future of human-agent interaction, starting with your browser.
- AgentGPT - Deploy autonomous AI agents in your browser. 
- doBrowser - An AI-powered Chrome extension that understands natural language and takes actions in your browser on your behalf.
- Surf.new - An open-source playground for chatting with different web agents. 
- OpenAI Operator - OpenAI's AI agents that can browser the web for you.
- Skyvern-AI - Framework to automate browser-based workflows. 
- Proxy by Convergence - Proxy is your AI-powered digital assistant that explores the web and executes tasks through simple conversation.
- Google Project Mariner - A research prototype exploring the future of human-agent interaction, starting with your browser.
- Runner H - Runner H is a state-of-the-art AI agent that will allow anyone to automate complex, cumbersome, multi-step tasks without repetitive and manual input.
- AgentGPT - Deploy autonomous AI agents in your browser. 
- Agent-E - Agent & framework with HTML DOM distillation. 
- Kura - Web Agents for the Enterprise.
- Manus - A general AI agent that can execute long running tasks across tools like browsers, terminals, and text editors.
- Yutori - A multi-agent system that executes browser-based tasks in parallel given a natural language prompt.
- Automina - AI browser automation tool with natural language control.
- rtrvr.ai - AI Web Agent Chrome Extension that autonomously does tasks, scrapes to Sheets, and calls API's – all with just prompts and your own browser!
- Agent-E - Agent & framework with HTML DOM distillation. 
- Kura - Web Agents for the Enterprise.
- Manus - A general AI agent that can execute long running tasks across tools like browsers, terminals, and text editors.
- doBrowser - An AI-powered Chrome extension that understands natural language and takes actions in your browser on your behalf.
- WebSurfer (Autogen) - MultimodalWebSurfer is a multimodal agent that can search the web and visit web pages. 
- Magentic-One - A generalist multi-agent system for solving complex tasks including surfing the web via Autogen's MultimodalWebSurfer.
- Harpa.ai - An AI-powered Chrome extension & browser agent that understands natural language and takes actions on your behalf.
- Magentic-One - A generalist multi-agent system for solving complex tasks including surfing the web via Autogen's MultimodalWebSurfer.
- Yutori - A multi-agent system that executes browser-based tasks in parallel given a natural language prompt.
- Automina - AI browser automation tool with natural language control.
- rtrvr.ai - AI Web Agent Chrome Extension that autonomously does tasks, scrapes to Sheets, and calls API's – all with just prompts and your own browser!
- Nanobrowser - An open-source & local-first AI web agent Chrome extension with flexible LLM options and multi-agent system. 
-
Computer-use Agents
- Anthropic Computer Use - Computer use agent that can control your browser.
- Self-Operating Computer Framework - A framework to enable multimodal models to operate a computer. 
- Highlight - Highlight AI lets models understand your desktop activity. Get stuff done faster.
- OpenInterpreter - An open-source CLI based agent that can write & execute code as well as control your browser. 
- UI-TARS - A GUI agent model designed to interact seamlessly with GUIs using human-like perception, reasoning, and action capabilities. 
- Anthropic Computer Use - Computer use agent that can control your browser.
- Self-Operating Computer Framework - A framework to enable multimodal models to operate a computer. 
- Highlight - Highlight AI lets models understand your desktop activity. Get stuff done faster.
- OpenInterpreter - An open-source CLI based agent that can write & execute code as well as control your browser. 
- UI-TARS - A GUI agent model designed to interact seamlessly with GUIs using human-like perception, reasoning, and action capabilities. 
-
-
Featured (new releases)
- Opera Agentic Feature - Opera announces a new agentic feature for its browser, showcasing innovative web agent integration.
- Opera Agentic Feature - Opera announces a new agentic feature for its browser, showcasing innovative web agent integration.
-
Benchmarks & Research
-
Dev Tools
- WebVoyager (Benchmark) - Vision-enabled web agent using GPT-4V for real-world website interaction. 
- Web Agent Leaderboard - Web agent leaderboard compiling different AI agent products and how they perform on the widely used WebVoyager benchmarks. 
- Web Games by Convergence - a collection of challenges designed for testing general-purpose web-browsing AI agents. 
- Bananalyzer - An open-source evaluation framework for web-based AI agents. 
- Mind2Web - A large-scale dataset for generalist web agents. 
- Web Games by Convergence - a collection of challenges designed for testing general-purpose web-browsing AI agents. 
- Bananalyzer - An open-source evaluation framework for web-based AI agents. 
- Mind2Web - A large-scale dataset for generalist web agents. 
- World of Bits: An Open-Domain Platform for Web-Based Agents - OpenAI's research paper that introduces World or Bits: a platform where agents complete tasks on the internet by performing low-level keyboard and mouse actions.
- MiniWoB++ - A classic suite of 104 mini web browser tasks in a synthetic environment. It's is an extension of the OpenAI MiniWoB benchmark. 
- WebCanvas - An online evaluation framework for dynamic web environments. Tests agents on live websites. 
- WebGPT - OpenAI's browser-assisted question-answering research project.
- World of Bits: An Open-Domain Platform for Web-Based Agents - OpenAI's research paper that introduces World or Bits: a platform where agents complete tasks on the internet by performing low-level keyboard and mouse actions.
- MiniWoB++ - A classic suite of 104 mini web browser tasks in a synthetic environment. It's is an extension of the OpenAI MiniWoB benchmark. 
- WebShop - A simulated e-commerce shopping environment with 1.18M real Amazon products. 
- WorkArena - A suite of 33 browser-based tasks for enterprise "knowledge worker" scenarios. 
- BrowserGym by ServiceNow - A gym environment for web task automation. 
- WebCanvas - An online evaluation framework for dynamic web environments. Tests agents on live websites. 
- WebGPT - OpenAI's browser-assisted question-answering research project.
- WebShop - A simulated e-commerce shopping environment with 1.18M real Amazon products. 
- WebVoyager (Benchmark) - Vision-enabled web agent using GPT-4V for real-world website interaction. 
- WorkArena - A suite of 33 browser-based tasks for enterprise "knowledge worker" scenarios. 
- BrowserGym by ServiceNow - A gym environment for web task automation. 
-
-
AI Web Automation Tools
-
Computer-use Agents
- Asteroid.ai - Hosted Browser Agents for SMEs to automate complex workflows. 
- PulsarRPA - AI-powered browser automation for data extraction. 
- Cekura.io - An AI browser agent that helps companies maintain up-to-date documentation.
- Dex by Dexterity - An AI coworker embedding into and controlling your browser.
- Autobrowser - A free, experimental Chrome extension that leverages Claude Computer Use to automate tasks in your browser.
- Bytebot - Bytebot provides AI-powered scraping automations that evolve with your target sites.
- Runcopycat - A no-code browser automation platform that turns screen recordings into reusable automated workflows.
- PulsarRPA - AI-powered browser automation for data extraction. 
- VimGPT - Experimental project using GPT-4 Vision to browse the web via the Vimium extension. 
- Cekura.io - An AI browser agent that helps companies maintain up-to-date documentation.
- Dex by Dexterity - An AI coworker embedding into and controlling your browser.
- Starizon.ai - Browser assistant for web task automation.
- Autobrowser - A free, experimental Chrome extension that leverages Claude Computer Use to automate tasks in your browser.
- Runcopycat - A no-code browser automation platform that turns screen recordings into reusable automated workflows.
- BrowserGPT - Browser extension for page summaries and Q&A.
- Browse.ai - Chrome extension webscraping that can leverage AI for structured data extraction.
- Strawberry Browser - A personal assistant that sits in your browser, automates repetitive web actions, learns your workflows.
- Deta.surf - An integrated platform that combines a browser, file manager, and AI assistant with browser-level context.
- Comet by Perplexity - An AI-powered browser by Perplexity. Not much more details out yet.
- Dia Browser - Dia Browser is envisioned as an entirely new web browser built with AI at the center by The Browser Company (Arc).
- Ottogrid - Spreadsheet based web agents to automate manual research.
- Starizon.ai - Browser assistant for web task automation.
- BrowserGPT - Browser extension for page summaries and Q&A.
- Browse.ai - Chrome extension webscraping that can leverage AI for structured data extraction.
- Strawberry Browser - A personal assistant that sits in your browser, automates repetitive web actions, learns your workflows.
- Deta.surf - An integrated platform that combines a browser, file manager, and AI assistant with browser-level context.
- Comet by Perplexity - An AI-powered browser by Perplexity. Not much more details out yet.
- Dia Browser - Dia Browser is envisioned as an entirely new web browser built with AI at the center by The Browser Company (Arc).
- Ottogrid - Spreadsheet based web agents to automate manual research.
-
Dev Tools
- Langchain Playwright toolkit - Toolkit integration with AI agents.
- Browserbase - A headless browser API for AI workflows.
- Stagehand - AI web browsing framework. 
- AutoGPT - Experimental agent for task completion and web browsing. 
- Bytebot - Containerized computer use agent framework with a virtual desktop environment. 
- Steel.dev - Open-source headless browser API built specifically for AI agents and apps. 
- Omniparser - Tool for parsing GUIs for vision based agents. 
- LaVague - Framework for natural language web automation. 
- Tarsier - Vision utilities library for web interaction agents. 
- Steel.dev - Open-source headless browser API built specifically for AI agents and apps. 
- AutoGPT - Experimental agent for task completion and web browsing. 
- Omniparser - Tool for parsing GUIs for vision based agents. 
- LaVague - Framework for natural language web automation. 
- Langchain Playwright toolkit - Toolkit integration with AI agents.
- Bytebot - Containerized computer use agent framework with a virtual desktop environment. 
-
-
AI Web Scrapers/Crawlers
-
Dev Tools
- FireCrawl - APIs for turning websites into LLM-friendly markdown. 
- Crawl4AI - Open-source LLM Friendly Web Crawler & Scraper. 
- ScrapeGraphAI - Python scraper based on AI. 
- WebAgent (OpenAgents) - The web-browsing agent module of the OpenAgents platform (HKU). Enables autonomous navigation of websites via natural language, as part of a larger multi-modal agent framework. 
- FireCrawl - APIs for turning websites into LLM-friendly markdown. 
- Crawl4AI - Open-source LLM Friendly Web Crawler & Scraper. 
- ScrapeGraphAI - Python scraper based on AI. 
- WebAgent (OpenAgents) - The web-browsing agent module of the OpenAgents platform (HKU). Enables autonomous navigation of websites via natural language, as part of a larger multi-modal agent framework. 
- Expand.ai - Turns any website into a type-safe API you can rely on.
- LLM Scraper - Uses LLMs for intelligent scraping and content understanding. 
- Expand.ai - Turns any website into a type-safe API you can rely on.
- LLM Scraper - Uses LLMs for intelligent scraping and content understanding. 
- SpiderCreator - Create complex Playwright spiders with natural language prompts. 
-
-
Web Search & Query Tools
-
Dev Tools
- AgentQL - A query language and toolkit that makes the web AI-ready. 
- SerpAPI - Search API that provides Google Search results for your agents.
- Serper.dev - Performant and cost effective search API that provides Google Search results for your agents.
- Jina.ai - Neural search platform for web data.
- AgentQL - A query language and toolkit that makes the web AI-ready. 
- Serper.dev - Performant and cost effective search API that provides Google Search results for your agents.
-
-
Tutorials & Guides
-
Dev Tools
- LangGraph WebVoyager Tutorial - Tutorial demonstrating how to build a web navigation agent using LangGraph Agents, Vision Models, and Web Voyager.
- Build an AI Browser Agent - Step-by-step guide to create an AI that browses the web using Playwright and the Browser-Use library.
- Install & Run Browser-Use Locally - Instructions on installing the open-source Browser-Use agent with a local LLM.
- Build a Browser Agent with DeepSeek - Walks through deploying a Browser-Use web UI agent powered by the DeepSeek model on a cloud VM.
- Build a Browser Agent with DeepSeek - Walks through deploying a Browser-Use web UI agent powered by the DeepSeek model on a cloud VM.
- LangGraph WebVoyager Tutorial - Tutorial demonstrating how to build a web navigation agent using LangGraph Agents, Vision Models, and Web Voyager.
- Build an AI Browser Agent - Step-by-step guide to create an AI that browses the web using Playwright and the Browser-Use library.
- Install & Run Browser-Use Locally - Instructions on installing the open-source Browser-Use agent with a local LLM.
-
-
Interested in implementing Steel?
-
Dev Tools
-
-
Join the Community
Programming Languages
Categories
Sub Categories
Keywords
openai
10
llm
9
ai
7
agent
6
gpt
6
ai-agents
6
python
6
gpt-4
6
artificial-intelligence
4
langchain
4
scraper
4
browser-automation
4
scraping
3
rpa
3
playwright
3
automation
3
autonomous-agents
2
agentgpt
2
agi
2
web-scraping
2
autogpt
2
web-crawler
2
baby-agi
2
next
2
t3
2
crawler
2
ai-scrarper
2
ai-rpa
2
ai-crawler
2
t3-stack
2
research
2
nodejs
2
javascript
2
pyautogui
2
interpreter
2
ai-tools
2
llm-evaluation
2
llm-agent
2
benchmark-framework
2
puppeteer
2
llama
2
browser
2
ui
2
tool-learning
2
semantic-parsing
2
chatgpt
2
anthropic
2
computer-use
2
docker
2
qemu
2