What problem does it solve?
Build a production-ready, AI-powered data collection agent for any public data source. Runs on a schedule, enriches results with a free LLM, stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
Core Features & Use Cases
The Three Layers
Three-layer architecture: Collect → Enrich → Store, where Scraper, AI (LLM), and Storage orchestrate end-to-end data flows.
- Free Stack: Scraping with requests/BeautifulSoup, JS-rendering with Playwright, AI enrichment with Gemini Flash, storage in Notion/Sheets/Supabase, and scheduling via GitHub Actions.
- AI-driven enrichment: Score, summarize, classify, and persist insights; learn from user feedback to improve over time.
- Use Cases: Monitor job boards, prices, news, GitHub repos, sports results, events, and other public data sources.
Quick Start
Configure your environment, add a data source, and run the agent to start scraping on a schedule.