Awesome AI Security Tools
Section: Scanners, Evals & Guardrails · 🟢 — Programmable guardrails (input/output/dialog/retrieval rails) for LLM apps. (NVIDIA) · updated 2026-08-17)
FreshScore 85
Entry
NeMo Guardrails
Appears in 6 awesome lists
NVIDIA's programmable guardrails toolkit: define input, dialog, retrieval, execution, and output rails that intercept the agent loop at five distinct layers using the Colang DSL. The execution rail layer specifically governs what tools the LLM can invoke and what their inputs/outputs may contain —…
Open github.comnvidia-nemo/guardrails
Found in these lists
Awesome Harness Engineering
Section: Security, Sandbox & Permissions · NVIDIA's programmable guardrails toolkit: define input, dialog, retrieval, execution, and output rails that intercept the agent loop at five distinct layers using the Colang DSL. The execution rail layer specifically governs what tools the LLM can invoke and what their inputs/outputs may contain —…
FreshScore 88
Awesome local LLM
Section: Security and Sandboxing · an open-source toolkit from NVIDIA for easily adding programmable guardrails to LLM-based conversational systems
FreshScore 87
Awesome Open Source AI
Section: 10. AI Safety, Alignment & Interpretability · Programmable guardrails toolkit for LLM-based conversational systems. Uses Colang DSL to define safety rules, dialog flows, and content boundaries. Integrates with LangChain, LangGraph, and LlamaIndex for production deployments. Apache 2.0 licensed.
FreshScore 89
Awesome Production Machine Learning
Section: Privacy and Safety · NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
FreshScore 92
awesome-python
Section: LLM and Inference · NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
FreshScore 81
Often listed next to it
promptfoo
Test your prompts, models, RAGs. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality. LLM evals for OpenAI/Azure GPT, Anthropic Claude, VertexAI Gemini, Ollama, Local & private models like Mistral/Mixtral/Llama with CI/CD
In 11 listsDetails
E2B
Firecracker microVM sandboxes purpose-built for agent tool loops: ~150ms cold start, Python/JS SDKs, open source. The clearest reference implementation of "code execution as a harness primitive" rather than a CI system bolted on.
In 7 listsDetails
Guardrails AI
Input/output validation framework for building reliable AI applications. Detects and mitigates risks through composable validators for PII, toxicity, prompt injection, and structured output validation. Features Guardrails Hub with 50+ pre-built validators. Apache 2.0 licensed.
In 6 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
Agent Governance Toolkit
🟢 — Multi-language toolkit for policy-enforced agent tool calls and audit records, with optional identity, MCP-gateway, sandboxing, reliability, and compliance components. (Microsoft) — note: official public preview; APIs and deployment patterns may change before general availability. · updated…;…
In 5 listsDetails
garak
The LLM vulnerability scanner. Probes models for hallucinations, data leakage, prompt injection, misinformation, toxicity, and jailbreaks. Extensive plugin-based architecture with 100+ vulnerability probes. Apache 2.0 licensed.
In 4 listsDetails
CubeSandbox
Tencent Cloud's production-validated microVM sandbox for AI agents: sub-60ms cold start via snapshot cloning, <5MB per-instance overhead, and true kernel-level isolation with eBPF-enforced network policies. E2B-compatible drop-in replacement that demonstrates how hyperscale cloud infrastructure…
In 4 listsDetails
OpenShell
Open-source policy-driven sandbox runtime for autonomous AI agents, announced at GTC 2026. Enforces security constraints at the kernel level via Landlock LSM (filesystem), seccomp BPF (syscalls), and an OPA/Rego-evaluated HTTP CONNECT proxy (network) — constraints are enforced on the environment…
In 4 listsDetails