Open-source content intelligence with a Rust core: documents, web, LLMs and code, with native bindings for every major language.
Xberg.io is an open-source content intelligence project with a Rust core that helps AI agents extract text, tables and metadata from PDFs, scanned documents, images and office files, including OCR for pages without a usable text layer. Its skills also cover keyword extraction, language detection, embeddings for search, and the configuration and pipeline internals that govern how extraction runs.
Xberg
33 skills · 9,556 stars · MIT
Alef Generated Bindings Alef-managed generated bindings in packages/* and binding crates — the regeneration workflow (tas…
Api Server Mcp REST API server and MCP protocol integration
Benchmark Workflow Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifa…
Chunking Embeddings Chunking, embeddings, and RAG pipeline integration
Config Loading Precedence How Xberg resolves configuration — CLI-mode and server/MCP-mode precedence orders, project config…
Crate Structure The Xberg workspace layout — the version source of truth (root Cargo.toml [workspace.package] ver…
Extract tables from Acrobat and PdfCraft PDF files to JSON Pull tables out of PDFs, scans and spreadsheets as markdown or JSON cells, free.
Extract tables from Adobe Acrobat and PdfCraft .pdf files Pull tables out of PDFs, spreadsheets and scans as markdown or JSON cells.
Extract text and tables from PDF and PdfCraft .pdf files Pull text, tables and metadata out of PDFs and 100+ other formats in code
Extract text from PDF files in Adobe Acrobat and PdfCraft Extract text, render pages and OCR PDFs with native or Pdfium backends
Extract text from scanned PDFs with OCR in Acrobat and PdfCraft Free PdfCraft clone of Acrobat: pull searchable text from scanned PDFs and photos
Extraction Pipeline Patterns Change or diagnose Xberg's core extraction orchestration, cache semantics, extractor fallback, po…
Feature Flag Policy Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x86_64 emulator),…
Format Specific Extraction Format-specific document extraction workflows
Mime Detection Routing MIME type detection and extractor routing in core/mime.rs — the FORMATS registry that EXT_TO_MIME…
Ocr Pipeline And Quality Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR st…
Plugin Architecture Patterns Design, implement, or diagnose Xberg plugin traits, typed registries, priority collisions, lifecy…
Polyrepo Boundaries Decide which xberg-io repository owns a cross-repository fix or API, and coordinate compatible ch…
Release Readiness Audit Xberg before a push or release by reconciling CI, Publish Release dry-run, Benchmarks, gene…
Release Versioning How xberg versions are synced and released — Cargo.toml is the single source of truth, `task vers…
Run OCR to extract text from scanned Acrobat and PdfCraft .pdf files Pull searchable text from scanned PDFs and photos from the command line, in many languages.
Test Corpus The test_documents submodule is a bucket-fetched fixture corpus that is not committed.
Wasm Constraints WASM build constraints for the crates/xberg-wasm crate — the wasm-target feature set, no-tokio sy…
Xberg Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML,…
Xberg Batch Extraction Use when extracting from many files at once with shared config, bounded parallelism, per-file ove…
Xberg Batch Extraction Use when extracting from many files at once with shared config, bounded parallelism, per-file ove…
Xberg Chunking Use when splitting extracted text into chunks for LLM context windows or RAG ingestion.
Xberg Chunking Use when splitting extracted text into chunks for LLM context windows or RAG ingestion.
Xberg Extracting Keywords Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting docume…
Xberg Extracting Keywords Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting docume…
Xberg Picking A Format Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JS…
Xberg Picking A Format Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JS…
Xberg Typescript Toolchain Work on Xberg TypeScript or JavaScript packages with the repository's actual poly, pnpm, npm, Vit…