Llama Guard is an LLM-based input-output safeguard model geared towards Human-AI conversation use cases.
WildGuard is an open, lightweight moderation tool for LLM safety that achieves three goals:
Cost / License
- Free
- Open Source
Application type
Platforms
- Self-Hosted
- Python
Encrypted - No logging DNS. A carefully selected collection of no-logging DNS providers that implement DNS over HTTPS or TLS or both.


+2
ShieldGemma is a set of instruction tuned models for evaluating the safety of text and images against a set of defined safety policies. You can use this model as part of a larger implementation of a generative AI application to help evaluate and prevent generative AI...
Cost / License
- Free
- Proprietary
Application type
Platforms
- Self-Hosted
- Google Cloud Platform
A text classification model that can be used as a guardrail to protect against toxic prompts and responses in conversational AI systems.
A suite of easy-to-use tools for managing and supporting IT assets across organisations – helping to save time and money as well as adding security.


+2














