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
BrowserOperator/browser-operator-core
Browser Operator is a desktop AI browser released under the BSD-3-Clause license and distributed as prebuilt applications for macOS and Windows. Instead of adding an assistant panel to an existing browser, the project builds the agent into the browsing environment itself, so that specialised agents can drive pages, extract content and chain steps across sites to complete a task the user described in natural language. The stated positioning is privacy first: the agent logic and page processing run on the user machine, and pairing the browser with a local model server such as Ollama through LiteLLM allows fully offline operation with no data leaving the device. Model access is configurable rather than fixed to one vendor. The settings offer OpenRouter as the beginner path with sign-in through the browser and access to several hundred models, OpenAI and Groq through an API key, and LiteLLM as a proxy route for local models and advanced setups, which in practice covers Claude, GPT, Gemini and Llama family models. The repository tags also list MCP client support and LangGraph, indicating that agents can reach external tools and are wired as graph-structured workflows. Documented use cases are literature review and data collection, competitive and market research, product comparison, review analysis and price monitoring, and business work such as talent sourcing, lead generation and compliance audits. System requirements are modest, with 8 GB of RAM recommended as a minimum. The project is aimed at knowledge workers and researchers who repeat structured browsing work and want it automated without sending their browsing data to a hosted operator service.
https://github.com/BrowserOperator/browser-operator-core
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.