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
Berkeley-NLP/Agent-Eval-Refine
The Berkeley-NLP/Agent-Eval-Refine project presents a comprehensive framework for the autonomous evaluation and refinement of digital agents that interact with web environments and mobile devices. This project is based on the research paper "Autonomous Evaluation and Refinement of Digital Agents" accepted at COLM 2024 and awarded Best Paper at the MAR Workshop of CVPR 2024. The core contribution lies in designing evaluation models that can autonomously assess and improve the performance of digital agents, which are capable of browsing the web or controlling iOS and Android devices. The repository includes evaluation models and code located in the `agent_eval` directory, which supports both open-weight models and GPT-4V-based models for assessing agent performance. It also provides tools for refining agents and running experiments on iOS and Android emulators found in the `exps` directory. Notable implementations include the Reflexion + GPT-4 agent achieving state-of-the-art results on the WebArena benchmark and a refined CogAgent model that significantly improves success rates on iOS tasks. The project offers a Python binding for mobile device emulators to facilitate end-to-end evaluation and refinement workflows. It supports evaluation of agent trajectories stored in a unified format, with utilities for inspection, annotation, and dense captioning of screenshots using a vision-language model (VLM). The captioner model enhances the modular evaluator by providing detailed descriptions of visual inputs, aiding in reasoning about agent behavior. Extensive datasets, models, and agent trajectories are publicly available on the Huggingface Hub, enabling reproducibility and further research. The repository also includes detailed instructions for setup, evaluation, and refinement processes, along with scripts and notebooks to assist users in deploying and improving digital agents across different platforms. Overall, this project advances the field of autonomous digital agents by integrating evaluation and refinement into a unified system, leveraging state-of-the-art AI models to push the boundaries of agent performance in complex interactive environments.
https://github.com/Berkeley-NLP/Agent-Eval-Refine
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.