search-api 开源项目推荐（339 个）

manticoresoftware /manticoresearch

开源搜索数据库，支持全文、向量和混合搜索，具备实时索引和 SQL。

firecrawl /firecrawl-mcp-server

官方 Firecrawl MCP 服务器，面向 AI 智能体的上下文 API：搜索、抓取网页并与之交互，还可通过任意 MCP 客户端进行解析、爬取、映射、Agent 和 Monitor。

airweave-ai /airweave

面向 AI 智能体的开源上下文检索层

oxylabs /google-ai-mode-scraper

大规模抓取 Google AI Mode 响应且不被封禁。

fatwang2 /search2ai

自托管的AI代理搜索网关。统一搜索、新闻和页面提取，带有提供者回退。REST API，MCP服务器和TypeScript库。

oxylabs /ai-scraper-py

AI Scraper is a powerful scraping tool and scrape agent built to automate data extraction with unmatched precision. Ideal for scalable AI scraping tasks across diverse web sources, this tool simplifies complex scraping operations into efficient, intelligent workflows.

koursaros-ai /nboost

NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)

oxylabs /agent-browser

Execute complex automation scripts via remote cloud sessions , featuring integrated residential proxies , automated CAPTCHA solving , and native JavaScript rendering for the toughest dynamic websites.

oxylabs /web-scraper-api

All-in-one web scraping API for real-time, large-scale data extraction – proxies, CAPTCHA management, JS rendering, and parsing in a single request returning HTML or structured JSON.

robbyczgw-cla /hermes-web-search-plus

Give your Hermes agent the web as real sources, never a made-up answer — multi-provider search and extraction with an optional local, key-free DonSeTch option.

oxylabs /AI-Search-py

Turn plain English queries into structured web data, featuring automated markdown extraction and full JavaScript rendering for dynamic websites.

graphlit /graphlit-mcp-server

Model Context Protocol (MCP) Server for Graphlit Platform

zqzten /alfred-web-search-suggest

Alfred search suggest workflow for various popular websites.

vakovalskii /searcharvester

面向 AI 智能体的自托管搜索与 markdown 采集器。SearXNG（100+ 个引擎）+ FastAPI + trafilatura。兼容 Tavily 的 /search 以及支持尺寸预设和分页的 /extract。一条命令即可运行的 Docker Compose。

meilisearch /meilisearch-mcp

A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.

NetLops /SoSearch

🔎 One query. Three search engines. Self-hosted web search for AI agents via HTTP API or MCP. Aggregates DuckDuckGo, Brave & Yahoo. Built with Rust. No API keys required.

IslamHouse-API /multilingual-quran-hadith-islamic-content-database-api-hub

Official multilingual Islamic API hub providing Quran, Hadith, books, articles, fatwas, videos, and verified translations through IslamHouse.com, QuranEnc.com, and HadeethEnc.com — free, reliable, and officially supervised.

brcrusoe72 /agent-search

Self-hosted search API + MCP server for AI agents. Bundles SearXNG. Zero API keys, one-command deploy. Open-source alternative to Tavily, Exa, and Serper.

isnow890 /naver-search-mcp

MCP server for Naver Search API integration. Provides comprehensive search capabilities across Naver services (web, news, blog, shopping, etc) and data trend analysis tools via DataLab API.

firish /webfetch

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.