farhanlodi31 

High-accuracy native .NET OCR powered by EasyOCR's neural models running on ONNX Runtime. No Python required.

CUDA GPU execution provider for EasyOcrSharp. Adds Microsoft.ML.OnnxRuntime.Gpu so detection and recognition run on NVIDIA GPUs.

High-accuracy native .NET OCR powered by PaddleOCR's neural models (DB detection, text-line orientation, SVTR/CRNN recognition) running on ONNX Runtime. No Python required.

Universal, manifest-driven, pure-managed model inference for .NET. All-in-one: ONNX loader, multi-dtype CPU engine, tensors, pipeline, plus audio (FFT/log-mel) and text (WordPiece) front ends — zero external,... More information

ImageSharp-based image pre/post-processing adapter for ModelSharp — resize/normalize tensor preprocessing and classification/detection postprocessing.

Fast, lightweight, and flexible object-to-object mapper for .NET with support for nested objects, lists, enums, and sub-object injection.

Model acquisition for ModelSharp — download and cache ONNX / GGUF / safetensors models (and their external-data + tokenizer files) from Hugging Face Hub or any URL, then run them in one line via... More information

CUDA GPU execution provider for PaddleOcrNet. Adds Microsoft.ML.OnnxRuntime.Gpu so detection, classification and recognition run on NVIDIA GPUs.

ILGPU GPU execution backend for ModelSharp — C# kernels JIT-compiled to CUDA / OpenCL, with a CPU fallback and whole-graph GPU dispatch.

A fully managed imaging library for .NET: PNG, JPEG (incl. progressive and CMYK), WebP, GIF, BMP, TIFF, TGA, Netpbm, QOI and ICO codecs, an Image<TPixel> processing pipeline (resize, crop, rotate, blur/sharpen,... More information

High-performance persistent collection library with ACID transactions, indexing, and advanced data structures

A RAG (Retrieval-Augmented Generation) framework for .NET. Build intelligent applications with document ingestion, text chunking, embedding generation, vector storage, semantic search, reranking, and answer... More information

Command-line OCR powered by EasyOcrSharp — EasyOCR's neural models on ONNX Runtime, no Python required. Scans images, PDFs, globs and folders to text, JSON, hOCR, ALTO or TSV, writes searchable PDFs, and... More information

Production-ready hybrid post-quantum cryptography library for .NET authentication. Combines classical ECDSA P-256 with post-quantum ML-DSA-65 (FIPS 204) to provide quantum-resistant JWT signing and validation.... More information

Optional ONNX Runtime add-on for EasyImageSharp: document orientation (PP-LCNet), page dewarp (UVDoc), super-resolution (Real-ESRGAN contract), learned denoise (DnCNN contract), background removal / saliency... More information

Native .NET document layout analysis: detect and classify page regions (title, text, table, figure, caption, formula, header/footer…), order them the way a human reads, and optionally OCR text regions through a... More information