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.

Building blocks for rapid development of GenAI applications

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

Framework for LLM evaluation, guardrails and security

Make AI work for Everyone - Monitoring and governing for your AI/ML

First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)

Trustworthy question-answering AI plugin for chatbots in the social sector with advanced content performance analysis.

LLM proxy to observe and debug what your AI agents are doing.

A Python library for guardrail models evaluation.

💂🏼 Build your Documentation AI with Nemo Guardrails

This repo hosts the Python SDK and related examples for AIMon, which is a proprietary, state-of-the-art system for detecting LLM quality issues such as Hallucinations. It can be used during offline evals, continuous monitoring or inline detection. We offer various model quality metrics that are fast, reliable and cost-effective.

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

We compared LangChain, Fixie, and Marvin

AI Assistant for FMBench (foundation model benchmarking tool)

AI Tool RAG System: LlamaIndex-powered discovery engine for AI tools with Telegram bot interface using NeMo Guardrails

CSV validator for Guardrails AI

E-commerce fashion assistant with Chatgpt, Hugging Face, Ltree and Pgvector.

Agentic Safety Framework

Demo showcase highlighting the capabilities of Guardrails in LLMs.

The Modelmetry Python SDK allows developers to easily integrate Modelmetry’s advanced guardrails and monitoring capabilities into their LLM-powered applications.