WebFetch

概要

Local Large Language Models often lack the ability to browse the web, leaving them stuck with outdated information. WebFetch offers a powerful, self-hosted solution that integrates directly with local AI runtimes like LM Studio. It provides real-time data through tunable web search, leveraging over 70 configurable engines, and offers reliable, clean content extraction from any URL using industry-standard parsing. This tool empowers local LLMs with up-to-date information, making them more versatile for research, analysis, and general knowledge tasks, all while maintaining user privacy by being API-free and self-hosted.

主な機能

• Precision Search across 70+ configurable engines including academic and technical sources
• API-Free Freedom with no quotas or tracking
• Tunable Search & Clean Content Extraction
• Self-hosted and easy to set up with Docker and Node.js
• Clean Content Extraction using Mozilla Readability and JavaScript execution for dynamic pages
• 0 GitHub stars

ユースケース

• Conducting real-time research with local LLMs on current events or specific topics
• Extracting clean, AI-ready content from any URL for analysis or summarization
• Accessing up-to-date technical documentation or academic papers for AI-powered assistance