Libraries & frameworks
kreuzberg
kreuzberg-dev/kreuzberg
A polyglot document-intelligence engine that extracts text, tables, and metadata from 100+ formats via libraries, CLI, REST, and MCP server.
Topics
Related projects
xberg9.5kA polyglot document-intelligence engine that extracts text, tables and metadata for RAG pipelines and AI agents.
pdf-inspector19.9kA fast Rust library and CLI for PDF inspection, classification, and text extraction. It detects scanned versus text-based files, produces position-aware Markdown with tables, offers selective OCR, and ships Python, Node.js, and WebAssembly bindings.
ExtractThinker1.6kExtractThinker is a Python library that turns complex documents into validated, typed data. Define a Pydantic contract, choose a parser and LLM, then load, classify, split and extract.
pypdfium2857Python bindings to PDFium for rendering, inspecting, manipulating and creating PDF files, with a helper API and a small CLI.
mem068.8kA memory layer SDK for AI agents and assistants that stores, retrieves, and personalizes long-term context.
onyx33.4kAn open AI workspace that unifies enterprise search, RAG chat, custom agents, and any LLM provider.