Xberg: A Rust-Core Engine to Parse 100+ Document Formats
techNmak · x · 2026-08-14
Xberg is a fast and precise document intelligence engine designed to replace the multiple disparate libraries developers currently stitch together for data preprocessing.
- Universal parsing: Built on a Rust core, it supports over 100 formats including PDFs, Office files, images, emails, and audio, outputting a single unified format.
- Multimodal & OCR: Integrates various OCR backends like Tesseract, PaddleOCR, and VLMs, featuring fallback chains and confidence scores.
- Layout reconstruction: Supports complex layout and table reconstruction using models like PP-DocLayout-V3 and RT-DETR.
- Code & Audio: Offers code intelligence across 371 programming languages (extracting functions, classes, docstrings) and audio transcription via Whisper.
- Language bindings: Provides 15 language bindings (Rust, Python, Node.js, Go, etc.) to seamlessly integrate into existing RAG pipelines.
More from coding & agent
- DeepSeek Harness: ~20% of Project Commits Generated by OpenAI Codex — steipete · 2026-08-14
- PathSim: An Open-Source Python Framework for Dynamical System Simulation — tom_doerr · 2026-08-14
- Solving the Agent Memory Bottleneck: Merge Launches Unified Connective Infrastructure for Production AI — shensi · 2026-08-14
- Grok Build Launches Workflows: Orchestrate Hundreds of Agents in Parallel — elonmusk · 2026-08-14
- Amazon Engineer's 4-Agent System Spirals Out of Control: A Cautionary Tale — DuaneJRich · 2026-08-14
- AI Agent Spends 40 Minutes on a 2-Click Task, Exposing Browser Automation Flaws — StartClean337 · 2026-08-14