kreuzberg: Kreuzberg is a high-performance, polyglot library designed to extract text and metadata from over 57 file formats, including comprehensive OCR capabilities. Built with a Rust core, it offers native speed processing, memory efficiency, and the ability to generate embeddings without requiring a GPU, making it highly versatile for various data extraction and processing tasks.; paiml-mcp-agent-toolkit: PMAT (Pragmatic Multi-language Agent Toolkit) is a comprehensive tool designed to analyze code quality, grade technical debt, and generate AI-ready context for various LLMs. It supports over 17 programming languages and offers features like mutation testing, repository scoring, and semantic search across git history.
Automated extraction of text, metadata, and structured data from diverse document types.
Generate AI-ready context for large language models