stagehand

🧳 A state-of-the-art multi-agent travel planning system powered by OpenAI Agents SDK and LangGraph orchestration. Leverages Stagehand/Playwright for browser automation, Supabase for data persistence, and Firecrawl/Tavily for intelligent research.

🐋 Official Stagehand AI Browser Automation library for Golang users. Built by Browserbase.com

🦀 [ALPHA] Official Stagehand AI Browser Automation SDK for rust users. Built by Browserbase.com

Apply to your dream jobs without lifting a finger.

Chrome extension to record, import, and run playwright scripts directly in your browser

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

Chart Meme Generator ( Next.js + Gemini AI + Stagehand + Browserbase )

Deterministic PDF rendering for Laravel. Real Chromium, explicit readiness, per-render artifacts.

Official Stagehand AI Browser Automation SDK for Ruby users. Built by Browserbase.com

MCP server for Grammarly AI detection and plagiarism scoring via Stagehand + Browserbase browser automation, with Claude-powered text optimization

Agentic browser automation built from small, reusable pieces.

☕ [ALPHA] Official Stagehand AI Browser Automation SDK for Java users. Built by Browserbase.com

Effect-first browser automation for Cloudflare Workers. Give it a prompt, get a completed task.

🐘 [ALPHA] Official Stagehand AI Browser Automation SDK for PHP users. Built by Browserbase.com

Live browser sessions for AI agents. Watch your agents work in real-time with CDP screencasting, natural language control, and full browser automation on Cloudflare Workers.

A prompt eval playground for stagehand steps.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic.

Demos as code — generate demo videos, interactive walkthroughs & marketing captures from your running web app. CI-native, agent-ready (MCP)

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.