browser-use/browser-use
Browser-use is a project that enables AI agents to control and automate web browsers, allowing users to perform complex tasks through natural language commands and AI-driven browser interactions.
Awesome AI Agents › Browser Automation Tools
Browser Automation Tools
CloakHQ/CloakBrowser
CloakBrowser provides a stealthy Chromium binary with C++ source-level fingerprint patches to pass bot detection, serving as a drop-in Playwright/Puppeteer replacement.
jackwener/OpenCLI
OpenCLI converts any website or local tool into a command-line interface, enabling both human interaction and AI agent automation through logged-in browser sessions.
browserbase/stagehand
Stagehand is a production-ready AI web browsing framework that combines code and natural language to enable reliable and extensible browser automation.
browser-use/web-ui
A web-based user interface, powered by Gradio, for interacting with browser automation agents, supporting various LLMs and custom browser configurations.
citrolabs/ego-lite
ego lite is a specialized browser designed for AI agents to perform web automation in parallel with human browsing, offering isolated workspaces and enhanced page snapshots.
jo-inc/camofox-browser
Camofox-browser is a stealth headless browser server, powered by Camoufox (a Firefox fork), designed for AI agents to bypass bot detection and Cloudflare, offering a Puppeteer/Playwright alternative.
microsoft/fara
Fara-7B is a compact and efficient agentic small language model by Microsoft designed to perform multi-step computer tasks through visual interaction, achieving state-of-the-art performance on web automation benchmarks while enabling on-device deployment for privacy and low latency.
oxylabs/ai-crawler-py
AI-Crawler by Oxylabs AI Studio is an AI-powered web crawling tool that extracts relevant data from websites using natural language prompts and outputs structured JSON or Markdown formats for easy integration.
nat/natbot
Natbot is a project that enables controlling a web browser using GPT-3 to perform intelligent and flexible browser automation tasks.
hyperbrowserai/HyperAgent
HyperAgent is an AI-enhanced browser automation tool that uses large language models to enable natural language commands for scalable, customizable web automation and data extraction.
oxylabs/browser-agent-py
Python SDK for the Oxylabs AI Studio Browser Agent, which drives a real browser from natural-language instructions and returns JSON, Markdown, HTML or screenshots.
McGill-NLP/webllama
WebLlama is a project that builds advanced AI agents using Meta's Llama 3 model to browse the web by following instructions and engaging in dialogue, surpassing GPT-4V in web navigation benchmarks.
browserable/browserable
Browserable is an open-source, self-hostable browser automation library that enables AI agents to navigate websites, perform tasks, and extract information efficiently.
leoning60/browsernode
TypeScript port of Browser-use that lets LLM agents drive a Playwright-controlled Chromium browser, exposing an Agent class compatible with the original Python project APIs and features.
OSU-NLP-Group/Mind2Web
Mind2Web is a comprehensive dataset and framework for developing and evaluating generalist web agents that follow natural language instructions to perform complex tasks across diverse real-world websites.
zabirauf/AutoGPT.js
AutoGPT.js is an open-source project that brings the powerful capabilities of AutoGPT to run directly in web browsers, enabling local GPT agent execution with enhanced accessibility and privacy.
THUDM/AutoWebGLM
AutoWebGLM is a large language model-based automated web navigation agent that enhances web browsing efficiency and accuracy through innovative algorithms, hybrid training, and bilingual benchmarking.
browser-use/vibetest-use
Vibetest MCP is an automated QA testing tool that uses multiple Browser-Use agents to detect UI bugs, broken links, and accessibility issues on live and local websites.
stanford-mast/blast
BLAST is a high-performance serving engine that provides an OpenAI-compatible API for integrating web browsing AI with features like concurrency, streaming, caching, and automatic parallelism to enable efficient and interactive AI-driven web applications.
inspectIT/inspectIT
inspectIT is an open-source Application Performance Management tool for monitoring and analyzing Java EE applications with end-to-end tracing and browser end-user monitoring.
BrowserOperator/browser-operator-core
Open-source AI browser for macOS and Windows in which specialised agents work together to run research, shopping and business tasks on the web, with model calls routed to OpenRouter, OpenAI, Groq or local models.
mayt/BrowserGPT
BrowserGPT enables users to control their web browser using natural language commands by integrating GPT-4 with Playwright for seamless AI-driven browser automation.
reworkd/bananalyzer
Banana-lyzer is an open-source AI agent evaluation framework for web tasks that uses Playwright to run structured and reproducible tests on static snapshots of websites, supporting diverse datasets and multiple evaluation criteria.
vdutts7/gpt4V-scraper
GPT-4V Web Agent is an AI-powered tool that can visually perceive, control, and navigate web browsers to automate web scraping, data extraction, and interactive browsing tasks.
posgnu/rci-agent
RCI Agent for MiniWoB++ is a Python-based project that uses pre-trained language models to solve computer tasks in the MiniWoB++ benchmark by leveraging a novel RCI prompting scheme for improved task execution guided by natural language.
Berkeley-NLP/Agent-Eval-Refine
Berkeley-NLP/Agent-Eval-Refine is a framework for autonomous evaluation and refinement of digital agents that interact with web and mobile environments, featuring state-of-the-art models and tools for improving agent performance.
OSU-NLP-Group/WebDreamer
WebDreamer is a project that uses large language models as world models of the internet to enable model-based planning for web agents, improving their efficiency and performance on web interaction tasks.
reidbarber/webmarker
WebMarker is a tool that visually marks interactive elements on web pages to enhance their use with vision-language models for improved web automation and interaction.
magicgh/Self-MAP
Self-MAP is a project that advances multi-turn instruction following for conversational web agents using fine-tuned models and the MT-Mind2Web dataset, as presented in ACL 2024.