浏览器与 Web Agent

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

8.1M 可观测/月 120.5k ★ ▲ 554 ★/周 3/3 当前信号

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

5.3M 可观测/月 199.9k ★ ▲ 2.3k ★/周 3/3 当前信号

Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.

1.3M 可观测/月 87.1k ★ ▲ 410 ★/周 3/3 当前信号

Mastra is the modern TypeScript framework for AI-powered applications and agents.

13.8M 可观测/月 29.4k ★ ▲ 168 ★/周 3/3 当前信号

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

424.8k 可观测/月 71.5k ★ ▲ 220 ★/周 3/3 当前信号

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.

1.4M 可观测/月 32.8k ★ ▲ 111 ★/周 3/3 当前信号

Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.

837.2k 可观测/月 7.8k ★ ▲ 45 ★/周 3/3 当前信号

A metasearch library that aggregates results from diverse web search services

5.3M 可观测/月 3.1k ★ ▲ 14 ★/周 3/3 当前信号

Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

49.3k 可观测/月 12.2k ★ ▲ 112 ★/周 3/3 当前信号

Exa MCP for web search and web crawling!

253.9k 可观测/月 5.2k ★ ▲ 9 ★/周 3/3 当前信号

Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client

73.4k 可观测/月 1.4k ★ ▲ 10 ★/周 3/3 当前信号