Tagny

About

Tagny provides a suite of practical web-centric tools designed to expand the capabilities of locally hosted Large Language Models. It enables LLMs to interact with the internet by fetching plain text content from specified URLs, extracting all hyperlinks from webpages, and performing real-time web searches using popular engines like Brave and DuckDuckGo. This integration allows LLMs to access current information and parse web content, significantly enhancing their utility for tasks requiring up-to-date or external data.

Key Features

• Perform web searches using the DuckDuckGo search engine.
• Designed for seamless integration with locally served LLMs via the MCP protocol.
• 1 GitHub stars
• Fetch plain text content from any given URL.
• Extract all hyperlinks present on a webpage.
• Perform web searches using the Brave search engine.

Use Cases

• Equipping LLMs with real-time web search capabilities for up-to-date information.
• Enabling LLMs to summarize or analyze content directly from web pages.
• Allowing LLMs to discover and navigate related information by extracting page links.