Keyword: web-scraping
- @hyperbrowser/sdkReleased3d agoVersion0.91.2
Node SDK for Hyperbrowser API
- firecrawl-cliReleased2d agoVersion1.19.21
Command-line interface for Firecrawl. Scrape, crawl, and extract data from any website directly from your terminal.
- cdp-tunnelReleased6d agoVersion3.6.0
Bridge Chrome's debugger API to WebSocket — control your existing browser with Playwright/Puppeteer via CDP
- @browserbasehq/orcaReleased2 weeks agoVersion3.5.1-preview.0
An AI web browsing framework focused on simplicity and extensibility.
- @hauntapi/mcp-serverReleased1 week agoVersion1.0.22
MCP web extraction for permitted public pages: no-key demo plus live URL-to-JSON and Markdown output with honest blocked-page errors
- shantycrawl-mcpReleasedyesterdayVersion1.0.0
Dynamic Firecrawl MCP server with lazy-loading tool architecture
- @hanivanrizky/nestjs-browser-actionReleased17h agoVersion0.19.0
Stealth browser automation module for NestJS (CloakBrowser + puppeteer-core)
- dom-compactReleased3d agoVersion1.1.0
DOM Compact - Convert webpage DOM tree to compact text format for LLM
- @gravity-platform/ingestReleased1 week agoVersion4.0.1
Data ingestion nodes for Gravity workflow system
- roam-mcpReleased5d agoVersion3.0.0
MCP server for browser automation — AI agents that roam the web like a human, with Cloudflare Turnstile bypass
- crawlforge-mcp-serverReleased10h agoVersion4.8.1
CrawlForge MCP Server - Professional Model Context Protocol server with 26 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama
- @thinkrun/cliReleased2d agoVersion0.1.30
CLI for controlling browsers via ThinkRun cloud and local infrastructure
- obscura-nodeReleased2d agoVersion1.1.0
Node.js wrapper for Obscura — the Rust-powered headless browser for AI agents and web scraping. Drop-in replacement for headless Chrome with Puppeteer and Playwright. Ultra-lightweight (~30 MB), instant startup, built-in stealth mode.
- crawl4ai-cloudReleased22h agoVersion1.4.0
Lightweight cloud SDK for Crawl4AI - mirrors the OSS API
- encrata-cliReleasedyesterdayVersion0.3.2
Encrata CLI — intelligence lookups from your terminal
- @vakra-dev/reader-jsReleased19h agoVersion0.3.1
JavaScript/TypeScript SDK for the Reader API
- lean-readerReleased5d agoVersion0.1.1
Token-minimized URL-to-clean-text reader for LLMs, with a token-savings receipt. MCP server + library.
- opendevbrowserReleased1 week agoVersion0.0.36
Browser automation runtime with snapshot-refs-actions, browser replay screencasts, public read-only desktop observation, and browser-scoped computer-use orchestration
- @xberg-io/opencode-crawlbergReleasedyesterdayVersion0.1.1
OpenCode tools for crawling and scraping with the crawlberg CLI.
- phantomwright-cliReleased6d agoVersion2.3.0
CLI for undetected browser automation with human simulation and captcha solving
- @browseros-ai/agent-sdkReleased3d agoVersion0.0.7
Browser automation SDK for BrowserOS - navigate, interact, extract data with natural language
- @larelabs/refinery-mcpReleasedyesterdayVersion0.1.6
MCP server for cleaning raw HTML into LLM-ready text with Refinery.
- clone-this-websiteReleased3d agoVersion1.0.3
Professional cross-platform website cloner with beautiful CLI interface
- @stack0/cliReleased3d agoVersion0.1.1
Stack0 CLI — manage your Stack0 resources from the terminal