AI chat moderation in Roblox — by meaning, not a word list

Cortex, an AI moderation tool for Roblox, replaces word-list chat filters with a model that reads message meaning, catching obfuscated toxicity while avoiding false positives. The tool bills on output tokens only, with cached repeated messages, and costs a fraction of a Robux. It is available as a free open beta with an open-source kit on GitHub.

Word-list chat filters break the moment someone types a s s a s s i n with spaces, or a slur spelled with a 0 , or a perfectly innocent word that happens to contain a banned substring. You end up in an endless arms race patching your blocklist. An AI model reads the meaning of a message, so it catches obfuscated toxicity and stops false-flagging harmless phrases. js local Cortex = require game.ServerStorage.Cortex local ai = Cortex.new "YOUR KEY" local verdict = ai:ask "You moderate a kids' game chat. Reply with exactly one word: SAFE or BLOCK.", message if verdict == "BLOCK" then -- don't send it end The reply is one word, so it's cheap: with Cortex https://cortex-rbx.github.io you're billed on output tokens only , and repeated messages are served from cache for free — so moderating your whole chat costs a fraction of a Robux. You pay in Robux, no credit card, and the key stays server-side. BLOCK verdicts so you can tune the prompt.Free open beta and open-source kit: https://github.com/cortex-rbx/roblox-ai-kit https://github.com/cortex-rbx/roblox-ai-kit · demo: https://cortex-rbx.github.io https://cortex-rbx.github.io