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
unclecode/crawl4ai
Crawl4AI is an open-source Python library that turns any website into clean, LLM-ready Markdown for retrieval-augmented generation, data pipelines and AI agents. It wraps a browser-based crawler (built on Playwright) so pages that need JavaScript rendering are handled the same way as static ones, then converts the resulting HTML into structured Markdown while stripping navigation, ads and boilerplate. The project is installed with pip and configured through a setup command that provisions the underlying browser binaries. Beyond plain page-to-Markdown conversion, it supports extraction strategies driven by CSS selectors, XPath or an LLM, session and caching controls, proxy configuration and concurrent async crawling for scraping many pages at scale. It exposes both a Python API for embedding in data pipelines and an MCP server so an AI agent (in Claude Code, Codex or another MCP-capable client) can call it directly as a scrape/search/extract tool. The maintainers also run a hosted cloud version behind the same API for teams that do not want to operate the crawler themselves, while the open-source package remains free to self-host indefinitely. The project is popular as a data-ingestion layer for RAG systems: rather than each agent or pipeline writing its own scraping and cleanup code, Crawl4AI centralizes fetching, rendering and Markdown conversion so the output is directly usable as LLM context. It has an active release cadence, a Discord community and PyPI distribution with substantial monthly download volume, reflecting its role as general-purpose web-ingestion infrastructure for the broader LLM tooling ecosystem rather than a narrow one-off scraper.
https://github.com/unclecode/crawl4ai
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.
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.
lexmount/moli
Rust headless browser built for AI agents, with on-demand layout and rendering plus a CLI and CDP/WebDriver Classic/BiDi servers for lightweight page fetching and browser-use workloads.
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.