jev_antispam_bot
minimal grammY anti-spam bot that asks Jev about each message, with ten test files behind it.
何を判断するか
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
The community list's one-line summary does not say which question type this project uses. Read the source to find out — we would rather leave this blank than guess.
コンテンツ審査の他のプロジェクト
Jev Moderation BotDiscord bot that scores incoming messages for phishing, spam, and social engineering with Jev and drives a four-stage escalation ladder, injecting pardoned messages back into context as verified-safe precedent.jev-spam-evalzero-shot spam classification with Jev `Boolean` questions, benchmarked against TF-IDF baselines.mastra-jev-moderationMastra input processor that asks Jev a `Boolean` "must this message be blocked?" plus a category `Choice` in one request, aborting the turn at 0.7 and failing open behind a deadline and circuit breaker; in production it blocked 9/9 hostile and 0/49 real messages at ~0.4 s median, about 4× cheaper than an LLM moderator.Jev Chat for Twitchbring-your-own-key Chrome extension that reads a Twitch channel's chat over the anonymous IRC WebSocket, asks Jev one category `Choice` per message in batches of 20, and shows a second column of only the messages matching a chosen intent (helpful, questions, funny, feedback); about 504 input tokens per message, roughly $0.15 per hour on a 2-message-per-second chat and $0.76 per hour at 50 per second.