GH Repository · ScrapeGraphAI
Scrapegraph-ai
Python scraper based on AI
- stars
- 31,050
- 30-day movement
- +15251/day
- Related entries
- 60
- Connections
- 2
python/uvmakedockerfirecrawl-alternativewebscrapingweb-scraperweb-searchweb-data-extractionscrapingweb-scrapingragscraping-pythonpythonweb-datallmai-searchweb-crawlerai-scrapingcrawlermarkdownlarge-language-modeldata-extractionweb-crawlersPython
Scrapegraph-ai is a Python-based web scraper that uses large language models to drive scraping and crawling, tagged around RAG, markdown output, and web data extraction. The repository ships an AGENTS.md and includes toolchain files for Docker, Make, and Python (uv).
Reach for it when you want LLM-guided scraping and crawling in Python rather than hand-written extraction rules.
Use it to
- Scrape web pages with LLM-driven extraction
- Crawl sites and collect web data
- Feed scraped content into RAG pipelines
- Extract data as markdown
- Explore a self-described firecrawl alternative
For Python developers building AI-powered scraping pipelines
- Role
- rag
- Language
- Python
- Licence
- MIT
- Forks
- 3,126
- Open issues
- 6
- Last push
- 2026-09-07
- Latest release
- v0.2.8 · 2024-04-26
topicsweb-scrapingllmragcrawlerdata-extractionpython