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
leoning60/browsernode
Browsernode is a TypeScript implementation of Browser-use, the Python library that connects LLM agents to a real web browser. It aims for API and feature parity with the upstream project while keeping everything in the Node ecosystem, so JavaScript and TypeScript teams can automate web tasks without a Python runtime. Installation is a single npm package plus Playwright and a Chromium download; Node 20.19.4 or newer is required, and the README notes that Bun is not supported because of a Playwright bug. Provider API keys are read from a .env file. The programming model is small: construct a chat model such as ChatOpenAI from the browsernode/llm entry point, create an Agent with a natural-language task string and that model, then await agent.run. The returned history object carries the executed steps and token usage. Both CommonJS require and ESM import styles are documented, and scripts can be run directly with tsx. The agent works by reading the page, indexing interactive elements and emitting structured actions such as clickElement or done, which are echoed to the console during a run so the trajectory can be followed step by step. Custom functions extend the action set, which the examples use for tasks like saving results to a file or writing a document in Google Docs and exporting it as PDF. The repository ships an examples directory covering custom functions, use cases and user interfaces, including a Gradio demo, and there is an interactive command-line client. Documentation lives on a separate site. Reported demos include collecting the most valuable companies into a text file and navigating between Wikipedia articles, with the transcript showing failed attempts as well as successes. It suits developers who want browser-driving agents inside an existing TypeScript codebase.
https://github.com/leoning60/browsernode
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.