getmaxun/maxun

Health v2 · maintenance only

Adoption not part of the score

17299 stars · 1495 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Maxun is an open-source no-code platform for web scraping, crawling, search, and AI-powered data extraction that turns websites into structured APIs. It offers a visual browser recorder, scheduled monitors, LLM-driven extraction agents, and self-hostable deployment with API, SDK, CLI, and MCP interfaces.

Use cases

• scrape product prices from an e-commerce site without writing code
• turn a website into a structured REST API
• crawl an entire site and export pages as markdown for LLM training
• extract data from pages behind a login on a schedule
• monitor a webpage for changes hourly and get webhook alerts
• use natural language to extract structured data from complex sites
• convert PDFs into clean markdown or lists of links

When to choose

• you want no-code visual scraping with scheduled runs and API/webhook delivery
• you need to handle JavaScript-heavy or authenticated sites via real browser automation
• you want a self-hostable open-source alternative to proprietary scrapers
• you need LLM-ready markdown extraction and AI agents for complex sites

When to avoid

• you need a lightweight programmatic scraping library embedded in your own codebase
• you require high-volume scraping without credit-based limits and prefer writing custom scripts
• you need non-web data sources or heavy ETL transformations beyond extraction

Facets

application · maturity active

web-scraping agent-framework rag workflow-automation scheduling api-framework ocr crawlers artificial-intelligence self-hosted self-hosted cli no-code rpa browser-automation playwright data-extraction structured-api stealth-mode mcp web-crawler automation data-engineering web-server docker nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="getmaxun/maxun")