Open Source Projects tagged "Web Scraping"
A curated collection of the best open source projects tagged "Web Scraping". Each listing includes a website screenshot along with a detailed review of its features.
Turn any website into clean, AI-ready data via API
Stars
186,234Last commit
2 hours agoLicense
AGPL-3.0
API for AI agents to search, scrape, crawl, and interact with the live web, returning clean Markdown, structured JSON, or screenshots from any page.
Open Source Alternative to:
LLM-ready web crawler built for AI data pipelines
Stars
84,447Last commit
4 days agoLicense
Apache-2.0
Open-source web crawler and scraper that produces clean, structured output optimized for LLMs, RAG pipelines, and AI agents. Supports async crawling, CSS/XPath/LLM extraction, and stealth browser control.
Open Source Alternative to:
Chat with your documents using any LLM, fully private
Stars
66,573Last commit
11 hours agoLicense
MIT
A desktop and self-hostable AI app for chatting with documents, running local LLMs, and using AI agents without writing code or creating an account.
Open Source Alternative to:
No-code web scraping, crawling, and extraction platform
Stars
17,589Last commit
18 hours agoLicense
AGPL-3.0
Turn any website into structured data using a visual recorder, natural language prompts, or API. Includes proxy rotation, scheduling, and webhook integrations.
Open Source Alternative to:
Privacy-first knowledge base with any AI model you choose
Stars
16,290Last commit
9 hours agoLicense
Apache-2.0
Self-hostable NotebookLM alternative that lets teams build searchable knowledge bases from diverse sources, with support for any LLM and no data limits.
Open Source Alternative to:
Self-hosted SERP API for Google, Bing, Yandex, and more
Stars
1,427Last commit
11 hours agoLicense
MIT
Query Google, Bing, Yandex, Baidu, DuckDuckGo, and Ecosia through one REST API. Self-host free under MIT, or use the managed cloud option.
Open Source Alternative to:
Sent – A unified API for sending messages across SMS, RCS, and apps like WhatsApp.
Sent