List of open source safety models

[samidh]

Does ROOST maintain such a list?

[julietshen]

Right now a list kind of exists here, but I think there are many models missing (CoPE, gpt-oss-safeguard, Qwen3guard, etc). It probably makes sense to either add to this list and/or break it out so this repo has one too. What do you think?

[samidh]

Created a PR to add CoPE. For now put it in the "Classification" bucket, but it could also go in the "AI-powered Guardrails" bucket as there is increasing convergence between these two categories.

[andrewmchang]

The Hugging Face ML & Society team has also pulled together a super helpful collection of moderation models and datasets! Credit to @yjernite for this

[samidh]

How might I suggest additions to that HF collection, @yjernite?