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.

python nlp privacy transformers spacy named-entity-recognition data-privacy phi sensitive-data anonymization pii data-anonymization de-identification data-masking personally-identifiable-information data-obfuscation guardrails pii-detection data-redaction image-redactor

• Updated Nov 12, 2026
• Python

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.

automation ai llama gemma paperless mistral phi paperless-ngx ollama

• Updated Nov 11, 2026
• TypeScript

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

transformers llama mistral mlx phi llm

• Updated Jan 29, 2025
• Python

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

python data database catalog snowflake data-catalog aws-athena aws-redshift phi pii aws-glue

• Updated Jan 5, 2024
• Python

Phi3 中文后训练模型仓库

phi llm llm-chinese phi3 phi3-chinese

• Updated Nov 27, 2024
• Python

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

benchmark regex reliability evaluation dataset gpt phi large-language-models llm cc-by-nc-nd-4 open-compass chatglm qwen lm-evaluation llm-as-a-judge llm-as-evaluator xfinder reliable-evaluation key-answer-extraction judge-model

• Updated Nov 14, 2025
• Python

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.

openai multi-modal phi function-call qwq ai-agent llm llama-index chatglm internvideo tensorrt-llm qwen2 llama3 minicpm-v internvl qwen2-vl deepseek-r1 janus-pro olmocr qwen3

• Updated Dec 8, 2025
• Python

🧠 Living Consciousness Agent — PureField repulsion-field engine · Engine A ⇄ Engine G · Ψ=1/2 fixed point · 2,448 laws + 392 hypotheses

iit phi consciousness brain-inspired hexad ai-consciousness purefield consciousness-laws hexa-family repulsion-field engine-a engine-g psi-fixed-point

• Updated Aug 14, 2026
• Python

The open source PII and PHI redaction and de-identification engine

java redaction deidentification anonymize phi pii deidentify redact personally-identifiable-information protected-health-information nppi

• Updated Nov 6, 2026
• Java

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

open-source cloud ai moe llama gpt lora mistral phi fine-tuning peft large-language-models llm instruction-tuning llm-training finetuning-llms fine-tuning-llm qwen llama3

• Updated Nov 5, 2026
• Python

让医疗机构所有大模型流量：PHI 不外泄 · 模型走白名单 · 全量可审计 · 成本可控。

skills mcp medical healthcare compliance hipaa phi pipl presidio ai-coding claude-code openspec

• Updated Jun 5, 2026
• Python

Interact with any LLM service

openai llama fireworks jan mistral phi together lepton hyperbolic groq llm cerebras localai openrouter ollama lmstudio deepseek deepinfra novita nebius

• Updated Jun 8, 2025
• JavaScript

[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.

entropy decoding tree-search reasoning phi huggingface-transformers large-language-models chain-of-thought vllm training-free qwen deepseek large-reasoning-models test-time-scaling inference-time-scaling parallel-thinking varentropy

• Updated May 12, 2026
• Python

Philter redacts sensitive information such as PII and PHI in text.

redaction deidentification phi anonymization pii redact

• Updated Nov 4, 2026
• Java

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

android ai termux mamba mistral phi vicuna koboldai rwkv llamacpp ggml rwkv4 koboldcpp gguf tinyllama rwkvcpp tinyvicuna tinydolphin

• Updated Jun 21, 2024
• Shell

HIPAA compliant PHI access logging for Ruby on Rails.

rails gem hipaa phi phi-log

• Updated Nov 5, 2026
• Ruby

The open-source Three.js-based modern LLM Engine that runs in your browser via WebGPU compute.

chat threejs llama three webgpu phi llm qwen

• Updated Sep 30, 2026
• TypeScript

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

ai phi

• Updated Jun 5, 2026
• Rust

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

ai models llama mistral phi ollama qwen ollama-client ollama-gui ollama-app deepseek

• Updated Apr 2, 2025
• Swift

Local-first PII anonymization and de-anonymization in Go. Multilingual via GLiNER NER + 73 pattern recognizers. Self-host runs as a single binary that never leaves your network.

multilingual go agent privacy oss self-hosted named-entity-recognition hipaa data-privacy gdpr phi anonymization pii onnx de-identification guardrails pii-detection local-first llm gliner

• Updated Nov 8, 2026
• Go