Krawlr

View live

Company intelligence platform that gathers a structured profile of any company's business, financials, leadership and competitors — for analysts and AI agents alike.

Krawlr landing page — “AI-Powered Insights… Real-Time Decisions.”
Krawlr landing section — “Decode Any Company’s Digital DNA, Instantly.”
Krawlr dashboard with recent crawls and crawl analytics
Krawlr crawler — single URL and bulk scrape

A live SaaS platform that crawls a company's website, sitemap, SEC EDGAR filings, funding sources, news and leadership data in parallel, then merges everything into one normalized profile with a 0–100 data-quality score. Features include distributed crawling on Cloud Run through a Pub/Sub job queue, scheduled re-crawls with change detection, a REST API, and an MCP server backed by a from-scratch OAuth 2.1 authorization server, so Krawlr works as a connector inside Claude. The whole stack is containerized with Docker and shipped through a GitHub Actions CI/CD pipeline that builds, tests and deploys to Google Cloud.

Technologies

  • Python
  • FastAPI
  • asyncio
  • Scrapy
  • Cloud Run
  • Pub/Sub
  • Firestore
  • Cloud Storage
  • OpenAI
  • Gemini
  • MCP
  • OAuth 2.1
  • Docker
  • GitHub Actions
Next