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
lexmount/moli
Moli is an open-source, production-ready headless browser written in Rust and designed specifically for AI agent workloads such as crawling, browser-use agents, retrieval pipelines, evaluation environments and reinforcement-learning tasks. It bundles a complete browser runtime - V8 JavaScript engine, DOM, CSS, networking, storage, text shaping and software paint - but defers layout and rendering until an operation genuinely needs them, rather than continuously maintaining a fully rendered visual state the way a conventional browser does. Most agent requests only need page structure: extracting HTML or Markdown, querying the DOM, running JavaScript, or inspecting network and storage activity, all of which Moli serves directly from the browser runtime state without triggering layout or paint. Requests that need real geometry, such as reading an elements bounding box, hit-testing coordinates, or sending coordinate-based input, trigger one layout pass and keep only the latest frozen layout tree. Capturing a screenshot or polling a screencast goes further, rebuilding the frame and discarding the paint state once it has been read. This on-demand model keeps Moli fast and resource-light compared with browsers that render continuously. Moli is driven in several ways: a CLI (moli fetch) that can dump a page as Markdown, a compact semantic tree, a screenshot, a full-page image or a PDF, and that supports scripted interaction through an eval expression before exporting; and an automation server (moli serve) that exposes the same page state over Chrome DevTools Protocol, WebDriver Classic and WebDriver BiDi simultaneously, so tools such as Playwright can connect over CDP directly. An included WebMCP playground lets an agent list and call a sites native WebMCP tools. The project ships prebuilt binaries for Linux, macOS and Windows and is commonly installed by giving an AI agent a short prompt that fetches and runs the installer itself. It targets teams building browser-automation or web-extraction agents who want full JavaScript and DOM fidelity without the ongoing cost of a continuously rendered page.
https://github.com/lexmount/moli
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.
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.
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.