WebNexus
0
Enables intelligent document discovery and semantic search through powerful web crawling and a local Retrieval-Augmented Generation system.
关于
WebNexus is a powerful, open-source web crawling and Retrieval-Augmented Generation (RAG) system engineered for intelligent document discovery and semantic search. Operating entirely on your machine, it offers a sophisticated, private, and production-ready solution for managing and searching information. Utilizing state-of-the-art AI capabilities, advanced hybrid search techniques, and multi-strategy web crawling, WebNexus creates a comprehensive, locally-stored knowledge base perfectly optimized for technical content, documentation, and AI agent integration via the Model Context Protocol (MCP).
主要功能
- 0 GitHub stars
- FastAPI REST API with comprehensive endpoints for crawling, searching, and document management
- State-of-the-Art Hybrid Search with reranking and Stella EN 400M v5 Embeddings
- Multi-Strategy Web Crawling with JavaScript support and intelligent content extraction
- 100% Local-First Architecture with SQLite database and FAISS vector storage
- Full Model Context Protocol (MCP) Integration for AI agents with 3 production-ready tools
使用案例
- Creating searchable knowledge bases from API, framework, or GitHub documentation
- Aggregating and analyzing technical blogs, academic papers, and industry reports
- Integrating AI agents with web crawling and semantic search capabilities using MCP
Sponsored