Llama Guard
Meta's safety classifier for filtering prompts and AI responses
Launched yesterdaydev.meta.ai
Do you work on Llama Guard?
This listing is unclaimed. Claim it for free to edit the details, add screenshots and reply to reviews.
About Llama Guard
Developers building chatbots use Llama Guard to check what goes in and out of a model. This safety model from Meta classifies prompts and responses against a list of harm categories. Version 3 builds on earlier releases and adds extra categories. Teams place it as a guardrail around an LLM, flagging unsafe content before it reaches users. The same listing page covers Meta's Muse Code terminal agent, and access is paid.
Reviews
From people who have used it. One review per person, checked by a human.
No reviews yet. Be the first to say something useful.
