pebkac Chrome Nonautomation - A Local LLM-Driven Web Co-Browser using Smolagents, Zendriver, Trafilatura.

web Scrapper In Python

Telegram Mini App that saves internet articles to read them later

Lean Python tool for extracting clean, LLM-optimized markdown from web pages. Handles dynamic content with Playwright + Trafilatura for maximum information extraction efficiency.

ChatGPT AI Clone

Real-time AI search and chat backend with WebSocket streaming, powered by Tavily web search and Google Gemini for Flutter apps.

블로그 글을 전자책으로 만들어주는 서비스

🤖 Automated Q&A Dataset Generation Pipeline powered by LLMs. Multi-stage pipeline that searches, filters, extracts and transforms web content into high-quality question-answer datasets for LLM training. Supports multiple LLM providers (Groq, Mistral, Ollama) and search engines.

A web scraper with an LLM-powered document suggestion system that combines web crawling, data extraction, and advanced AI capabilities to recommend relevant documents.

This project is a Python-based web scraping tool that uses the Trafilatura library to extract and save text content from a list of specified websites. The program is designed to process multiple URLs, extract their main content, and save each website's content to a separate .txt file.

Summarize articles using NLTK, Gemini and Trafilatura

too many unstructured data, alok has too many req, seeing what helps

Trafilatura MCP Server

🤖 Collection of AI agents for web search, RAG, and multi-agent collaboration. Features phi-agent + Groq integration, Ollama support, DuckDuckGo/Google search, web scraping, and local knowledge base querying with vector embeddings.