SURF (Search Utility & Reading Framework) is an open-source API that bridges LLMs with the web. It provides a standardized interface for web search and content processing that preserves formatting of tables, code, and complex layouts.
Key features:
- Multiple search providers (SearXNG, DuckDuckGo, Brave)
- HTML cleaning and smart content extraction
- Model Context Protocol (MCP) integration for Claude and other AI assistants
- Self-deployable with minimal setup (Docker, bare metal, cloud)
- API key authentication
I built this to make it easier to add web capabilities to LLM applications without complex web scraping code, with emphasis on proper content formatting and attribution.
Repository: https://github.com/44za12/surf