Kreuzberg
Document intelligence for AI engineering workflows.
Kreuzberg is a document intelligence API that extracts structured, machine-readable content from PDFs, images, Office files, and 90+ other formats for use in AI pipelines. It offers OCR, layout detection, table extraction, semantic chunking, embeddings, and LLM-powered extraction in a single API call. Available as a managed cloud service or self-hosted, it is built on a high-performance Rust core for millisecond-speed processing.
Users send documents via API, SDK, CLI, or Docker; Kreuzberg processes them with OCR, layout detection, table extraction, and optional LLM-powered schema extraction, then returns a structured JSON response or delivers results via webhook.
AI engineers and developers building document intelligence pipelines, RAG systems, or AI agents
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.