Awesome GitHub RepositoriesBrowser Automation Orchestrators

This project is a structured educational resource and technical guide for designing and implementing autonomous systems using large language models. It provides a comprehensive curriculum and code samples focused on agentic design patterns, autonomous development, and the creation of systems capable of planning and executing multi-step tasks. The resource details the implementation of agentic retrieval-augmented generation, where models autonomously plan and refine data searches. It covers a wide array of orchestrators and design patterns, including metacognitive reflection for self-correctin

Fingerprint is a visitor identification and fraud detection platform that generates persistent, unique identifiers by analyzing browser and device attributes. By extracting technical signals from the client environment, it enables reliable user tracking across sessions without relying on traditional cookies. The platform distinguishes itself through its focus on high-accuracy identification and security-first architecture. It employs edge-side proxying to bypass ad-blockers and privacy restrictions, ensuring consistent data collection. To maintain data integrity, it uses cryptographic payload

ArchiveBox is a self-hosted archiving tool designed for personal digital preservation and research data management. It functions as an automated web preservation engine that monitors URL inputs from bookmarks, browser history, or manual entries to capture and store permanent, offline copies of web content. By utilizing headless browser automation, the system renders dynamic web pages to ensure that captured snapshots, PDFs, and media assets remain accurate and accessible even if the original source disappears. The project distinguishes itself through a modular extractor pipeline and a task-qu

Skyvern is an autonomous web navigation agent and browser-based workflow orchestrator that uses large language models to execute multi-step tasks on websites. By translating natural language instructions into actionable browser commands, the framework enables the automation of complex user workflows, including data extraction and interface interaction, without manual intervention. The platform distinguishes itself through a focus on secure, self-hosted infrastructure and stealth-oriented execution. It utilizes containerized browser isolation to maintain consistent environments and employs pro

Maxun is an open-source web scraping and automation platform designed to transform dynamic website content into structured data. By leveraging artificial intelligence to interpret natural language prompts, the system identifies page elements and extracts information without requiring manual selector configuration. It serves as a bridge between raw web content and intelligent workflows, providing structured outputs in formats optimized for large language model ingestion and agent-based applications. The platform distinguishes itself through its ability to handle complex, authenticated, and dyn

BrowserSync is a web development synchronization tool and live reload server. It functions as a local static web server, a reverse proxy server for existing sites, and a browser testing orchestrator that coordinates page state across different browsers and physical devices. The tool is distinguished by its ability to mirror user interactions, such as clicks, scrolls, and form inputs, in real time across all connected devices. It also provides a web-based device control interface and the capability to create public URL tunnels for remote testing of local sites. The system covers a broad range

get_jobs is a browser automation tool that submits resumes to multiple Chinese job platforms with minimal manual intervention. It orchestrates a sequence of browser actions to locate elements, fill forms, and click buttons, using a dual strategy of CSS selectors and XPath expressions for flexible and robust element targeting on dynamic pages. The tool requires only a single daily QR code scan to maintain a persistent session across runs, and it applies configurable filters—such as experience level, company blacklist, recruiter type, and keywords—to narrow job listings before submission. The t

This project is an LLM-powered web crawler and data extractor that uses large language models to navigate websites and parse content into structured JSON or Markdown formats. It functions as an automated browser orchestrator and domain discovery engine, interpreting plain English instructions to identify relevant pages and extract specific information. The system distinguishes itself through agentic browser automation, allowing it to perform human-like interactions such as clicking buttons and scrolling based on natural language commands. It employs goal-oriented crawling to analyze website s