ScrapeIQ combines headless browser automation with local RAG to extract structured insights from any website or document corpus. Deployable on-prem when compliance requires it.
Headless browser scraping
Playwright-driven extraction that handles dynamic content, auth, and anti-bot.
Local LLM enrichment
Ollama-powered semantic understanding that never leaves your network.
Vector store indexing
ChromaDB-backed retrieval for downstream querying and analytics.
Scheduled crawling
Cron-driven recurring jobs with diff detection and alerting.
Tech stack
- Python
- Playwright
- Ollama
- ChromaDB
- FastAPI
- PostgreSQL
Have a project in mind?
Tell us what you want to build. We respond within one business day.