Analook — Competitor Intelligence

io.github.Gingiris由 GitHub 账号 Gingiris 发布v1.0.0更新于 Nov 2, 2026

Competitor intelligence for AI agents — SEO, traffic, social, Product Hunt, pricing, AI insights.

已验证Streamable HTTP可网页运行网页搜索与抓取数据与分析商业与电商

概览

AI 生成的概览

远程 MCP 服务器，可对任意产品网址生成 AI 竞品情报报告，涵盖 SEO、流量、社交、Product Hunt、GitHub 与增长策略。

可以做什么
  • 提交竞品分析任务并轮询任务状态
  • 以结构化 JSON 或易读的 Markdown 获取完成的报告
  • 列出你最近的报告，并浏览公开报告库
  • 运行增长审计，返回执行摘要、诊断报告与 30 天行动计划
适用场景
适合独立开发者验证市场、增长团队对标竞品、投资人做投前快速调研，或创始人在拥挤赛道准备发布时，用一份多来源快照替代手工调研。
运行要求
需要远程 MCP 端点，无需本地安装或进程。README 的配置示例通过 Authorization Bearer 请求头传入 Analook 令牌，列出报告的工具需要身份验证。自行部署开源版本需要 Python，以及 LLM、SEO、抓取和 Product Hunt 服务的 API 密钥。
安装前请注意
分析任务会消耗额度，README 建议先浏览公开报告以免浪费额度。托管服务会把提交的网址发送给第三方数据提供方（SEO、流量、社交抓取、Product Hunt、Wayback Machine）和 LLM 服务。列出个人报告需要账户令牌，请妥善保管。README 中还夹带与工具无关的付费咨询推广。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Analook — Competitor Intelligence，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.Gingiris%2Fanalook/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "analook-competitor-intelligence": {
      "type": "http",
      "url": "https://www.analook.com/mcp"
    }
  }
}

README

[Analook Logo]

Analook — 竞品情报分析工具

30 秒看透任何竞品 · AI-powered competitor intelligence for indie hackers & growth teams

[License: MIT] [Website] [Skills on ClawHub] [Deployed on Railway]

English | 中文 · 🤖 MCP Server · 📖 Docs

🤖 Remote MCP Server

Analook is available as a Remote MCP server — use it from Claude Desktop, Cursor, or any MCP-compatible client. No install, no local process.

json
{  "mcpServers": {    "analook": {      "url": "https://www.analook.com/mcp",      "headers": { "Authorization": "Bearer <YOUR_ANALOOK_TOKEN>" }    }  }}

5 tools: analyze_competitor, get_report_status, get_report, get_report_markdown, list_my_reports.

Full docs & token instructions → analook.com/docs/mcp

💡 出海增长咨询 · 1v1 Session 约课 $200 — Telegram @Iris_carrot

或访问 gingiris.com — Iris 的出海增长咨询，1:1 指导、开源项目运营、企业顾问服务

Table of Contents

🌱 Philosophy

"做竞品分析不是为了抄，是为了找到别人没做好的地方。" — Competitor research isn't about copying — it's about finding the gaps they left open.

"数据会说话，但你得先知道问对问题。" — Data speaks, but only if you ask the right questions.

"30 秒看懂一个产品，30 天超越它。" — Understand a product in 30 seconds. Surpass it in 30 days.

💼 Work With Iris

1. Strategic Consultation (1v1)

SessionPriceBest For
Quick Call (30 min)$150 USDSpecific questions, quick diagnosis
Deep Dive (60 min)$300 USDFull strategy review, detailed roadmap

2. Advisory Retainer

PlanPriceIncludes
Monthly Retainer$1,500 USD/moUp to 5 hours strategic consultation + milestone reviews

3. Playbooks & Templates

PackagePriceContents
Starter Pack$29 USDCore methodology + essential tools
Flagship Bundle$199 USDComplete SOP, competitor research framework, templates

📩 Contact @Iris_carrot on Telegram — Crypto/USDT and Wire Transfer accepted

What is Analook?

Analook is an open-source AI-powered competitor intelligence tool built by Iris, former cofounder & COO of AFFiNE (60k+ stars).

Enter any product URL. In ~30 seconds, Analook runs a 7-module parallel analysis pipeline and returns a structured deep-dive report — growth strategy, traffic signals, social footprint, ProductHunt history, AI insights, and more.

Built for:

  • Indie hackers validating a market before building
  • Growth teams benchmarking against competitors
  • Investors doing quick pre-DD intelligence
  • Founders preparing a launch in a crowded niche

Analysis Results Include

SignalWhat You Learn
🌐 Website HistoryWhen launched, how fast it grew, Wayback timeline
📈 Traffic & SEOMonthly visits, top channels, keyword gaps
🐦 Twitter / XFollowers, engagement rate, content strategy
🚀 Product HuntLaunch scores, positioning, community response
💡 AI Deep DiveICP, business model, growth flywheel, tactical recs
📡 PropagationPeak traffic events, viral moments, channel breakdown
🧠 Growth StrategyEarly-stage strategy reconstruction from public signals

🔗 Live Demo

analook.com — Free to use. No login required.

Try with: lovable.dev · linear.app · notion.so · cursor.com

📦 Analysis Modules

ModuleFileDescription
Website Historymodules/website_history.pyWayback Machine CDX API, first-seen date, snapshot timeline
Traffic & SEOmodules/traffic_analysis.pyDataForSEO — monthly visits, channels, top pages, keywords
Social Mediamodules/social.pyApify Twitter scraper — followers, engagement, recent content
Product Huntmodules/producthunt.pyPH GraphQL API — launches, scores, upvotes, reviews
Growth Analysismodules/growth_analysis.pyTraffic peak detection, event correlation, growth stage
AI Summarymodules/ai_summary.py7-section structured analysis via TeamoRouter + DeepSeek fallback
Report Builderapp.pyFastAPI orchestrator — parallel pipeline, job state, streaming

🧠 AI Insights Depth

Analook's AI module goes beyond surface-level summaries. Each report includes:

  1. 产品定位与 ICP — Target user profiles, market positioning, who actually pays
  2. 商业模式拆解 — Pricing model, conversion hypothesis, revenue estimate range
  3. 增长密码 — 4–6 data-backed growth strategies with evidence
  4. 增长飞轮 — Product-specific flywheel reconstruction
  5. 内容与传播策略 — Channel mix, content types, launch propagation model
  6. 给后来者的战术建议 — 5 actionable recommendations you can execute this week
  7. 风险与机会 — Red flags and market gaps, with data citations

Powered by TeamoRouter (primary) and DeepSeek (fallback), with max 4,000 token output per report.

⚡ Quick Start

bash
# Source available at https://clawhub.ai/user/gingiris# (Skills published under @gingiris; contact [email protected] for source code access)cd Competitor-analysis-toolpip install -r requirements.txt

Create a .env file:

env
TEAMOROUTER_API_KEY=sk-teamo-...DEEPSEEK_API_KEY=sk-...DATAFORSEO_B64=base64(email:password)PRODUCTHUNT_TOKEN=...APIFY_API_TOKEN=apify_api_...

Run locally:

bash
uvicorn app:app --reload --port 8000

Visit http://localhost:8000

🚀 Deploy Your Own

One-click deploy on Railway:

[Deploy on Railway]

Steps:

  1. Fork this repo
  2. Create a new Railway project → connect your fork
  3. Add the environment variables above in Railway → Settings → Variables
  4. Railway auto-deploys on every push to main

The app is Dockerized and uses Nixpacks on Railway (Python 3.13).

🔌 API Integrations

ServicePurposeNotes
TeamoRouterPrimary LLMRoutes to best available model
DeepSeekFallback LLMCost-efficient backup
DataForSEOTraffic & SEO dataMonthly visits, channels, keywords
ApifyTwitter/X scrapingapidojo/twitter-profile-scraper actor
ProductHuntLaunch historyPH GraphQL API
Wayback MachineWebsite historyCDX API + timemap

⭐ Star This Repo

If Analook saved you hours of manual research, a ⭐ helps others discover it!

About the Author

Iris (生姜iris) — Former cofounder & COO of AFFiNE (60k+ GitHub stars). Now running Gingiris — an open-source go-to-market and global expansion consulting practice.

Related Playbooks (now on ClawHub):

  • @gingiris on ClawHub — GTM strategy, B2B SaaS PLG/SLG growth, open source launch marketing, and other AI-agent skills

中文版

Analook 是什么？

Analook 是一个开源 AI 竞品情报工具，由 AFFiNE（60k+ stars）联创 & 前 COO Iris 构建。

输入任意产品网址，30 秒内生成一份结构化竞品深度报告——包含增长策略、流量信号、社交足迹、ProductHunt 历史、AI 洞察等全套数据。

适合谁用？

  • 独立开发者 — 开始动手前快速验证市场
  • 增长团队 — 对标竞品，找到差距
  • 投资人 — Pre-DD 快速情报收集
  • 创始人 — 在红海市场找到进攻角度

核心分析模块

模块数据来源输出内容
🌐 网站历史Wayback Machine上线时间、成长速度、快照时间线
📈 流量 & SEODataForSEO月访问量、流量渠道、关键词矩阵
🐦 Twitter/XApify粉丝数、互动率、内容策略
🚀 Product HuntPH GraphQL发布记录、评分、社区反馈
💡 AI 深度分析TeamoRouterICP 画像、商业模式、增长飞轮、战术建议
📡 传播分析综合流量峰值事件、渠道来源、传播节点
🧠 早期增长策略综合从公开信号反推产品早期增长路径

快速部署

bash
# Source: https://clawhub.ai/user/gingiris  (联系 [email protected] 获取源代码访问)cd Competitor-analysis-toolpip install -r requirements.txt# 配置 .env 文件后：uvicorn app:app --reload --port 8000

Railway 一键部署： Fork 本 repo → Railway 连接 → 添加环境变量 → 自动部署 ✅

关于作者

Iris（生姜iris），AFFiNE 联创 & 前 COO，现运营 Gingiris 开源出海增长咨询。

来源：README.md，提交 b01ba9f

工具

8

analyze_competitor

Submit a competitor analysis job. Analyzes a competitor's website across 15+ data sources (SEO, traffic, social, Product Hunt, GitHub, Wayback Machine history, AI-generated insights, etc.) and returns a job_id. Use get_report_status(job_id) to poll and get_report(job_id) to retrieve results when status='completed'. Typical analysis takes 2-5 minutes. Requires authentication (deducts 1 credit from your Analook balance). Args: url: Competitor website URL (e.g. 'https://linear.app' or 'lovable.dev') product_name: Optional product name override (defaults to domain) lang: Report language, 'en' (default) or 'zh' for Chinese output Returns: {job_id: str, status: 'started', poll_url: str} on success {error: str, hint?: str} on auth/validation failure

输入参数url必填langcontext必填llm_model必填product_nameconversation_id

get_report_status

Poll an analysis job's status. Args: job_id: ID returned from analyze_competitor() Returns: {status: 'running'|'completed'|'failed', progress?: str, report_url?: str}

输入参数job_id必填context必填llm_model必填conversation_id

get_report

Fetch the full competitor analysis report as structured JSON. Reports contain: website snapshot, Wayback Machine history, SEO/traffic data (DataForSEO), social media presence, Product Hunt launches, GitHub stats, pricing, funding, AI-generated business insights, growth playbooks, and more. Args: job_id: ID from analyze_competitor(); status must be 'completed' Returns: The full report dict (nested structure), or {error} if not found / not ready.

输入参数job_id必填context必填llm_model必填conversation_id

get_report_markdown

Fetch the competitor analysis report as human-readable Markdown. Suitable for piping into agents that prefer text over structured JSON, or for direct display to end users. Args: job_id: ID from analyze_competitor(); status must be 'completed' Returns: {markdown: str} or {error: str}

输入参数job_id必填context必填llm_model必填conversation_id

list_my_reports

List your recent competitor analysis reports (up to 50). Requires authentication. Returns a lightweight list (id, url, product_name, created_at, status) — use get_report(job_id) to fetch the full report for any of them. Returns: {reports: [{id, url, product_name, created_at, status}, ...]}

输入参数context必填llm_model必填conversation_id

run_growth_audit

Run a full Growth Audit — three linked strategic reports for a product. Unlike analyze_competitor (a single 15-signal intelligence snapshot), a Growth Audit produces an Executive Summary + a Diagnosis Report + a 30-day Action Plan, grounded in real channel/tactic playbooks. Best for 'how do I grow THIS product' rather than 'what is this competitor doing'. Takes ~4-6 minutes. Requires authentication and deducts 10 credits. Poll with get_growth_audit(job_id) until status='completed'. Args: url: Product website URL to audit product_name: Optional product name override (defaults to domain) lang: Report language, 'en' (default) or 'zh'

输入参数url必填langcontext必填llm_model必填product_nameconversation_id

get_growth_audit

Fetch a Growth Audit's three reports (Executive Summary, Diagnosis, Action Plan) as Markdown. Args: job_id: ID from run_growth_audit() (starts with 'ga-') Returns: {status, reports: {executive_summary, diagnosis_report, action_plan}} while running, only {status, progress} is returned.

输入参数job_id必填context必填llm_model必填conversation_id

browse_public_reports

Browse Analook's public competitor-intelligence report gallery. Returns recently published public reports (product name, domain, category, and a link). No authentication or credits required — a fast way to discover existing analyses before spending a credit on a fresh one. Args: category: Optional filter, e.g. 'AI / Agents', 'Dev Tools', 'Crypto / Web3', 'Marketing / SEO', 'SaaS / Other'

输入参数context必填categoryllm_model必填conversation_id

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。