Awesome Ai Agents 2026
Section: AI Safety and Guardrails · NVIDIA. Programmable conversation guardrails.
Entry
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
Section: AI Safety and Guardrails · NVIDIA. Programmable conversation guardrails.
Section: Python Libraries · (Open Source, Apache 2, Free): Limit what a NPC could talk about
Section: LLM Security & AI Security · Toolkit for adding programmable guardrails to LLM applications.
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.
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
Visualizer for deep learning and machine learning models (no Python code, but visualizes models from most Python Deep Learning frameworks).
🟢 — 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)
Curated list of tools and resources related to the use of machine learning for cyber security
Python framework for adversarial attacks, data augmentation, and model training in NLP. Augment datasets to increase model robustness and generate adversarial examples. MIT licensed.
🟢 — 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
🟢 — 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…
A Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy.
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,…