What is Scrapegraph-ai built with?
Scrapegraph-ai is a Python repo. It uses AI through langchain-openai, langchain-ollama, LangChain, langchain-mistralai, langchain-aws, and 2 more, makes its content with beautifulsoup4 and html2text, validates its data with Pydantic and jsonschema, and is tested with playwright. It has 29,962 written lines, with 58 test files.
LinkedInRead on November 7, 2026, at commit 194055e. Read it as markdown
Backend
AI 7
langchain-openai16 files
- LangChain8 files
- langchain-classic2 files
- langchain-mistralai4 files
- langchain-aws3 files
- tiktoken1 file
Support
Content 2
- beautifulsoup44 files
- html2text1 file
Validation 2
- Pydantic31 files
- jsonschema1 file
Testing 1
playwright4 files
Other 6
- tqdm8 files
- python-dotenv10 files
- async-timeout1 file
- ddgs1 file
- semchunk1 file
- simpleeval1 file
Other repos with a similar stack
Ordered by how much of its stack they share with Scrapegraph-ai, then by stars.
- run-llamallama_index52.8k
LlamaIndex is the document processing platform for AI
6 of 18 in commonCompare → - bojieliai-agent-book57.2k
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
5 of 18 in commonCompare →
Frequently asked questions
What language is Scrapegraph-ai written in?
Scrapegraph-ai is written in Python, with 29,962 written lines.
Does Scrapegraph-ai use AI?
Yes. Scrapegraph-ai uses AI through langchain-openai, langchain-ollama, LangChain, langchain-mistralai, langchain-aws, langchain-classic, and tiktoken.
Does Scrapegraph-ai have tests?
Yes. Scrapegraph-ai has 58 test files and is tested with playwright.
Which repos have a stack like Scrapegraph-ai's?
The ones that share most of its stack:run-llama/llama_indexHKUDS/Vibe-TradingSignificant-Gravitas/AutoGPT
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.
Is it your repo? Add its badge, keep it up to date or take it down →
