โ† ํŠธ๋ Œ๋”ฉ

Tangerine Index๋Š” ChatGPT ์ดํ›„ ๋‚˜์˜จ ํ”„๋กœ๋•ํŠธ์™€ ์‚ฌ๋žŒ๋“ค์˜ ๋ฐ˜์‘์„ ์‹ฃ์Šต๋‹ˆ๋‹ค.

AnyCrawl

github.com

AnyCrawl ๐Ÿš€: A Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts structured SERP results from Google/Bing/Baidu/etc. Native multi-threading for bulk processing.

์˜คํ”ˆ์†Œ์Šค

github.com ๋ฐฉ๋ฌธ์™ธ๋ถ€ ์‚ฌ์ดํŠธGitHub3,527 ์Šคํƒ€์™ธ๋ถ€ ์‚ฌ์ดํŠธ

์„ค์น˜ยท์—ฐ๊ฒฐ

๊ณต์‹ MCP Registry, Homebrew, npm, PyPI, crates.io์—์„œ ์ €์žฅ์†Œ๋‚˜ ๋„๋ฉ”์ธ์œผ๋กœ ๋งž์ถฐ ํ•˜๋ฃจ ํ•œ ๋ฒˆ ๊ฐ€์ ธ์˜ต๋‹ˆ๋‹ค.

๋ฐ˜์‘ (1)

๋น„์Šทํ•œ ํ”„๋กœ๋•ํŠธ

์„ค๋ช…์ด ๋น„์Šทํ•œ ์ˆœ

  1. HyperCrawl

    Super-fast web crawling for LLM development

    Product Hunt์ถ”์ฒœ 148hypercrawl.hyperllm.org์ตœ๊ทผ ๋ฐ˜์‘

  2. webclaw

    Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data โ€” all from Rust. CLI, REST API, and MCP server.

    GitHub์Šคํƒ€ 2,436github.comCLI์…€ํ”„ ํ˜ธ์ŠคํŒ…MCP ์„œ๋ฒ„์˜คํ”ˆ์†Œ์Šค์ตœ๊ทผ ๋ฐ˜์‘

  3. x-crawl

    Flexible Node.js crawler library

    GitHub์Šคํƒ€ 1,889github.com๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ์˜คํ”ˆ์†Œ์Šค์ตœ๊ทผ ๋ฐ˜์‘

  4. Yomuco

    A simple web crawling library for Node.js

    Hacker News23์ GitHub์Šคํƒ€ 34github.com๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ์˜คํ”ˆ์†Œ์Šค๋ฐ˜์‘ 2๊ฐœ์ตœ๊ทผ ๋ฐ˜์‘

  5. Draco

    A single-binary, self-hostable Firecrawl alternative in Rust

    Hacker News15์ github.com์…€ํ”„ ํ˜ธ์ŠคํŒ…์˜คํ”ˆ์†Œ์Šค์ตœ๊ทผ ๋ฐ˜์‘