Skip to content

Entry

NeMo Guardrails

Appears in 5 awesome lists

NeMo Guardrails is an open-source toolkit facilitating the integration of programmable guardrails, essential for steering and safeguarding AI agents' conversational outputs, into large language model-based applications github | research paper

Open github.comnvidia/nemo-guardrails

Found in these lists

Awesome Ai Agents 2026

Section: AI Safety and Guardrails · NVIDIA. Programmable conversation guardrails.

ActiveScore 70

Awesome AI Tools for Game Developers

Section: Python Libraries · (Open Source, Apache 2, Free): Limit what a NPC could talk about

StaleScore 41

Awesome OSINT List

Section: LLM Security & AI Security · Toolkit for adding programmable guardrails to LLM applications.

FreshScore 88

Hacking Tools

Section: AI & Machine Learning Security · NVIDIA's programmable guardrails toolkit using Colang-based policy language to define topical, safety, and action guardrails for LLM applications, supporting input, output, dialog, and retrieval rails.

FreshScore 90

Awesome AI Agents: Tools, Resources, and Projects

Section: Repositories · NeMo Guardrails is an open-source toolkit facilitating the integration of programmable guardrails, essential for steering and safeguarding AI agents' conversational outputs, into large language model-based applications github | research paper

SlowScore 66

Netron

Visualizer for deep learning and machine learning models (no Python code, but visualizes models from most Python Deep Learning frameworks).

In 16 listsDetails

Guardrails AI

🟢 — Python framework for adding input/output guards, validators, structured-output controls, and Guardrails Hub checks to LLM applications. (Guardrails AI) · updated 2026-08-26); Related: NeMo Guardrails · LLM Guard · Pydantic AI Shields integration (README recommends a successor)

In 7 listsDetails

Awesome ML for Cybersecurity

Curated list of tools and resources related to the use of machine learning for cyber security

In 3 listsDetails

TextAttack

Python framework for adversarial attacks, data augmentation, and model training in NLP. Augment datasets to increase model robustness and generate adversarial examples. MIT licensed.

In 6 listsDetails

Rebuff

🟢 — Archived prompt-injection detector (heuristics + LLM + vector DB + canary tokens). (Protect AI) — note: archived by the maintainer; retained as a historical prompt-injection defense reference. · updated 2024-01-25); Related: LLM Guard

In 5 listsDetails

ART

🟢 — Flagship machine-learning security library for evaluating and defending models against evasion, poisoning, extraction, and inference attacks across major ML frameworks. (LF AI & Data / IBM) · updated 2026-10-08); Related: Foolbox · PrivacyRaven · XLab adversarial-ML course (incomplete…

In 4 listsDetails

TensorFlow Privacy

A Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy.

In 4 listsDetails

Fiddler AI

The all-in-one AI Observability and Security platform for responsible AI. It provides monitoring, analytics, and centralized controls to operationalize ML, GenAI, and LLM applications with trust. Fiddler helps enterprises scale LLM and ML deployments to deliver high performance AI, reduce costs,…

In 4 listsDetails