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
THUDM/AutoWebGLM
AutoWebGLM is an advanced project focused on creating a large language model (LLM)-based automated web navigation agent designed to improve the efficiency and effectiveness of web browsing tasks. Built on the ChatGLM3-6B model, AutoWebGLM extends its capabilities to navigate the web more intelligently, addressing real-world browsing challenges. The project introduces several innovative features, including an HTML Simplification Algorithm inspired by human browsing behavior, which simplifies web pages to make them more comprehensible for LLM agents while retaining essential information. It employs a hybrid human-AI training approach that combines human expertise and AI-generated data to build a comprehensive web browsing dataset for curriculum training, enhancing the model's practical navigation skills. Additionally, the project leverages reinforcement learning and rejection sampling techniques to improve the model's understanding of web pages, browser operations, and task decomposition, enabling more efficient and accurate navigation. AutoWebGLM also presents AutoWebBench, a bilingual benchmark in Chinese and English for evaluating AI web navigation agents on real-world tasks, providing a valuable resource for testing and refining these systems. The project includes publicly available evaluation code, datasets, and modified environments such as WebArena and MiniWob++ to facilitate experimentation and benchmarking. Licensed under Apache-2.0, the repository supports research purposes and encourages citation of their KDD 2024 paper. Overall, AutoWebGLM represents a significant step forward in leveraging large language models for automated web navigation, combining innovative algorithms, training methodologies, and evaluation benchmarks to push the boundaries of AI-driven web interaction.
https://github.com/THUDM/AutoWebGLM
Also in 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.