browser-use
Verified · 42 days agoBrowser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
claude mcp add --transport http shadow-crawl https://shadowcrawl--devshero.run.tools
Self-hosted Rust binary for web search, extraction, and stateful browser automation with explicit anti-bot bypass (CDP rendering, proxy rotation, human-in-the-loop CAPTCHA solving). Technically substantial and honestly documented, but its headline capability — defeating Cloudflare/DataDome and scraping auth-walled sites — violates most target sites' ToS, so treat it as a liability decision, not just a tool choice. Note the project has been rebranded to CortexScout (repo renamed cortex-scout) and last push was ~a month ago. For self-hosters doing research scraping who accept the legal exposure.
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
MCP server for browser use access
Playwright Tools for MCP
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.