roost.tools / awesome-safety-tools
Mirror of https://github.com/roostorg/awesome-safety-tools
0
fork

Configure Feed

Select the types of activity you want to include in your feed.

Add gpt-oss-safeguard by OpenAI

https://github.com/openai/gpt-oss-safeguard

gpt-oss-safeguard is a set of open-weight safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks.

gpt-oss-safeguard was released by OpenAI in partnership with ROOST and Hugging Face after months of work, including evaluation and testing from ROOST and Discord.

Signed-off-by: Cassidy James Blaede <cassidyjames@roost.tools>

authored by

Cassidy James Blaede and committed by
GitHub d844dfba 14d98f24

+2
+2
README.md
··· 50 50 * a pretrained model for detecting lewd images 51 51 * [Sentinel by Roblox](https://github.com/Roblox/Sentinel/tree/main) 52 52 * a Python library designed specifically for realtime detection of extremely rare classes of text by using contrastive learning principles 53 + * [gpt-oss-safeguard by OpenAI](https://github.com/openai/gpt-oss-safeguard) 54 + * open-weight reasoning model to classify text content based on provided safety policies 53 55 54 56 ## AI-powered Guardrails 55 57 * [Llama Guard by Meta](https://github.com/meta-llama/PurpleLlama/tree/main/Llama-Guard3)