Xberg
A document-intelligence engine with a Rust core, language bindings, OCR, structured extraction, embeddings and CLI, REST and MCP interfaces.
About Xberg
Retrieval pipelines need to turn varied document formats into text, tables and metadata before indexing them.
Who it’s for
- Developers preparing documents for search and RAG
- Teams extracting structured data from mixed document collections
When to consider it
Consider Xberg when you want document extraction, OCR and retrieval preparation through one engine with bindings for several languages.
Tradeoffs & limitations
- The open-source libraries are MIT licensed; the managed Xberg Platform is a separate offering. ONNX Runtime features such as embeddings, layout detection and transcription require AVX/AVX2 instructions on x86_64 CPUs, and optional OCR and image codecs have extra installation requirements.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Xberg.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 30, 2026 · Prepared with AI assistance; not a hands-on benchmark.
- Xberg official website
- Official document extraction, OCR, embeddings and interfaces
- Installation dependencies and CPU restrictions
- Official repository and Kreuzberg-to-Xberg rebrand
- MIT licence
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Xberg official website
A document-intelligence engine with a Rust core, language bindings, OCR, structured extraction, embeddings and CLI, REST and MCP interfaces.
Based on official pages and announcements checked on 2026-10-30. No hands-on test, performance benchmark or popularity ranking is claimed.