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
oxylabs/browser-agent-py
Browser Agent is a hosted AI browser automation service from Oxylabs AI Studio, accessed through the oxylabs-ai-studio Python package. Instead of writing selectors and scripts as with Puppeteer or Selenium, the caller supplies a starting URL and either a natural-language prompt describing the task or a structured list of actions drawn from click, type, navigate, wait and extract. The agent then simulates a real user session, clicking links, filling forms, scrolling and navigating JavaScript-rendered pages, and finally returns the result in one of four output formats: structured JSON parsed against a schema, Markdown, raw HTML, or a base64-encoded PNG screenshot of the browser content. When JSON output is requested a schema is mandatory, and the SDK offers a generate_schema method that builds one from a short field description such as game name, platform, review stars and price. The main entry point is a BrowserAgent object constructed with an API key, whose run method takes url, user_prompt, output_format, an optional schema and an optional geo_location given as an ISO2 country code for proxy routing; the default output format is Markdown. Requirements are Python 3.10 or later and an API key, with a free trial granting a credit allowance. The README shows examples that search a sandbox store for a specific product and extract its price into a typed JSON structure, and that capture and save a screenshot of a home page. Documented use cases include e-commerce checkout simulation, travel search automation with filters, job posting scraping and event or ticket discovery. The FAQ notes that logins and form submissions are supported but that sites with advanced bot detection may require additional setup, and that users are responsible for complying with target site terms. A companion JavaScript SDK is published separately.
https://github.com/oxylabs/browser-agent-py
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.