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
magicgh/Self-MAP
Self-MAP is an advanced project focused on improving multi-turn instruction following for conversational web agents, as presented in the ACL 2024 paper titled "On the Multi-turn Instruction Following for Conversational Web Agents." The project provides an official implementation of the methods described in the paper and utilizes the MT-Mind2Web dataset, which is specifically designed for training and evaluating conversational web agents in multi-turn dialogue scenarios. The repository includes detailed setup instructions, requiring Python 3.11 or lower and installation of necessary dependencies. Users are guided to download the MT-Mind2Web dataset and configure paths for data and logs in configuration files. The project is divided into two main components: Candidate Generation and Conversational Action Planning. Candidate Generation involves fine-tuning models like DeBERTa-v3-base to rank and score element candidates within test sets, with scripts provided for training, evaluation, and generating pickle files for further use. Conversational Action Planning focuses on fine-tuning models such as FLAN-T5-base for predicting conversational actions, with support for distributed training across multiple GPUs. The repository also supports enabling various modules like generation, memory simplification, memory refinement, and multifaceted matching to enhance the model's capabilities. The codebase is derived from the Mind2Web project and is licensed under the MIT License, while the MT-Mind2Web dataset is available under the CC-BY-4.0 license. The project is well-documented, including citation information for academic use. Overall, Self-MAP aims to advance the state-of-the-art in conversational AI by enabling web agents to better understand and follow complex, multi-turn instructions in web-based interactions.
https://github.com/magicgh/Self-MAP
Also in Browser Automation Tools
unclecode/crawl4ai
Open-source Python web crawler and scraper that converts web pages into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an API and an MCP server.
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.
feder-cr/dots
dots is an open-source CLI/web agent pairing any OpenRouter model with a patched Firefox engine for undetectable, human-like browsing, with per-seed identities and persistent login profiles.
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.
lexmount/moli
Rust headless browser built for AI agents, with on-demand layout and rendering plus a CLI and CDP/WebDriver Classic/BiDi servers for lightweight page fetching and browser-use workloads.
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.