An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.

Phi3 中文后训练模型仓库

Scan databases and data warehouses for PII data. Tag tables and columns in data catalogs like Amundsen and Datahub

[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

Interact with any LLM service

The open source PII and PHI redaction engine

A set of bash scripts to automate deployment of GGML/GGUF models [default: RWKV] with the use of KoboldCpp on Android - Termux

HIPAA compliant PHI access logging for Ruby on Rails.

A cross platform library with C#/Swift/Kotlin/Python bindings for running Phi inference

Ollmao (OH-luh-MAO) is a native SwiftUI app that integrates with Ollama to run powerful AI models locally on your Mac.

.NET 8 API for document file format identification, text/metadata/attachment/embedded object/sensitive item (PII/PHI)/entity extraction.

A collection of classes for data representation from Base16 (hex) to Base2048 written in JavaScript.

AI voice assistant made with Streamlit python and powered by Gemini, Mistral and PHI-3

Common GLSL math constants (with 11 decimals) available both as ES modules strings and as GLSL files for use with glslify.

Torchsharp port of phi-series model

Interactive data visualisation in style of Martin Krzywinski's Pi day posters