MCP web research server (give Claude real-time info from the web)
web-research 开源项目推荐(2,775 个)
web-research 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 2,775 个仓库Claude Code 技能:免费使用带引用的 Google AI Mode 搜索。零配置设置、持久浏览器配置文件、查询优化。节省 Token 的网络研究。
MCP server for free Google AI Mode search with citations. Query optimization, CAPTCHA handling, multi-agent support. Works with Claude Code, Cursor, Cline, Windsurf.
基于 FastMCP 3 的确定性研究 MCP 服务器 — 5 引擎网页搜索、9 平台社交搜索、6 个学术数据库、新闻聚合、实体画像、冲突检测、文档分析。无需 API 密钥。服务器内无 LLM。为智能体链式调用提供结构化输出。
从您的终端访问网络。搜索、提取页面、获取可靠答案并进行深入研究,选择您喜欢的提供商。CLI、TypeScript 库和 Pi 扩展。
Deep research skill for AI agents: live web research, source reputation checks, safer URL fetches, and structured evidence feedback.
本地浏览器工具包:AI代理:深入调研与浏览器自动化,配合本地Chrome(CDP)+ Playwright。灵活、可扩展的脚本,用于网页导航、提取和工作流程自动化——专为可重复的研究和代理驱动浏览而打造。
浏览器优先的本地 AI 研究工作区,支持设备端 WebGPU 和 WASM 推理、免费网络上下文工具以及私有本地笔记。
一个兼容模型上下文协议(MCP)的服务器,专为全面网络研究设计。它使用 Tavily 的 Search 和 Crawl API 收集指定主题的详细信息,然后将这些数据结构化为适合 LLM 创建高质量 Markdown 文档的格式。
Multi-agent research assistant using OpenAI Agents SDK and Olostep to produce sourced Markdown research reports.
An interactive CLI research assistant that scrapes, sanitizes, and synthesizes web content locally or via Gemini/OpenAI/Claude, with Discord/Telegram alerts & built-in automation.
One SaaS URL in, a due-diligence-grade platform teardown out. A Claude Code skill.
Portable web-research and browser-automation SKILLs for Claude Code, Codex, and OpenCode — Playwright, Chrome DevTools, nodriver, and HTML-to-Markdown.
Agent-native browser and MCP server for lightweight, Chrome-free web discovery, with explicit escalation to Unchained for browser-only flows.
Copilot Context Optimizer is a VS Code extension that gives GitHub Copilot specialized tools to analyze files and process terminal commands efficiently without overwhelming chat context. It extracts only specific information needed instead of dumping entire files or verbose outputs, keeping conversations focused on problem-solving.
Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.
A Claude Skill that turns a CV into a structured, verified, bilingual Excel research file of companies to target — real web research, fit scoring based on your actual skills (not generic "hires fresh grads"), per-company salary estimates, and an actionable shortlist.
Autonomous coding agent with web research (Recon), adversarial plan debate, 5-tier cognitive memory, multi-model routing (Gemini + DeepSeek + Ollama), 24/7 loops, and $0 local mode. Apache 2.0.
A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten
Source-verified web research for GTM enrichment: every fact carries the URL that proves it, results are cached across runs, and paid providers run only when free ones fail.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/web-research。
- 该话题在 GitHub 上共有 2,775 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1333 Star,覆盖 5 种主要语言,数据更新于 2026-11-09。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。