A framework that finds and masks personal data in text, images and tables. It detects the data, then redacts or replaces it so it can be safely sent to a model.
All repositories
SecurityNVIDIA-NeMo
Guardrails
NVIDIA's toolkit for programmable rails in LLM-based conversational systems. Rules live in config and control what the bot talks about and does.
Who it is for
For people building a chatbot who want hard limits on what it may discuss.
How to start
- Install (Python 3.10 to 3.13):
pip install nemoguardrails - Create a config folder and describe your rules in YAML following the Usage section
- Load the config in Python and call the bot through it
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+177Sep 7 — Oct 6
Author's description
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
More in «Security»
A vulnerability scanner for LLMs: it runs a model through a set of probes for prompt injection, data leakage, toxicity and other failures. Works as a command-line tool.
A Python framework that checks LLM inputs and outputs with ready validators from Guardrails Hub and helps produce structured answers. It catches risks before a reply reaches the user.
Microsoft's framework for proactively finding risks in generative AI systems. It helps automate red teaming against models and applications.
Meta's generative AI safety project: the Llama Guard and Prompt Guard filter models, the Code Shield scanner and the CyberSec Eval test suites. It pairs defense with attack-based testing.
A security scanner for AI agents, MCP servers and skills. It checks configs and SKILL.md files for risky spots.