NVIDIA

Voice +2

NeMo

NVIDIA framework for building speech AI models, including ASR, TTS, translation, and speaker diarization

Coding +2

NeMo Agent Toolkit

Library for connecting, profiling and optimizing teams of agents across frameworks.

Security +1

OpenShell

Sandboxed runtime for autonomous agents, with declarative YAML policies enforced at the HTTP method and path level

Inference +2

Model Optimizer

Coding +1

TensorRT LLM

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.

Security

NeMo Guardrails

Open-source toolkit for adding programmable input, dialog, retrieval, execution, and output guardrails to LLM apps

Security

SkillSpector

Security scanner that checks AI agent skills for vulnerabilities, malicious patterns, and supply-chain risks before install

Inference

Switchyard

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility -

Security +1

NemoClaw

NVIDIA reference stack running OpenClaw, Hermes, or Deep Agents inside OpenShell sandboxes with managed inference and network policy

Security

Garak

Command-line vulnerability scanner that probes LLMs for jailbreaks, prompt injection, data leakage, toxicity, and other failures