What it does
One pass identifies toxicity, profanity, severity, language and evasion styles such as leetspeak or mixed scripts.
Apps & data pipelines
gg-friggin-ez
A Node.js toxicity screener tuned for romanized, code-mixed Indic text, with language and obfuscation signals beside the verdict.
Bookmark: gg-friggin-ez
Keep this in your collection.
Leave a noteWhat would you try with this?
: gg-friggin-ez
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
A developer can install this tool directly into your chat app. They set it up using an access key from TypeSafe or OpenRouter to review incoming messages. Because the built-in rules already spot disguised spellings and mixed-language insults, you can start screening chats right away.
Your developer can adjust the settings to hide obvious attacks while holding unsure messages for human review. Because automated filters can still misinterpret playful banter or make mistakes, you should have team members inspect flagged posts before banning any users.