🧠
New
·
Local AI · no OpenAI
The AI Moderator is an intelligent moderation system that automatically analyses every message in your server for harmful behaviour. When something is detected, the bot acts immediately according to your settings — issuing a warning, deleting the message, or simply logging it for your moderators.
Unlike most "AI" Discord bots, our detection runs entirely on our own servers. Messages are never forwarded to Google, OpenAI or any other external AI service.
Type a test message and watch our local AI score it live — the exact same model that protects your server.
Messages are analysed on our own infrastructure. No data to third parties, no tracking, no external APIs. Your community data stays yours.
Full detection in both English and Dutch. The model recognises toxicity equally well in both languages — no separate configuration needed.
Under 100 milliseconds per message. No matter how busy your server gets, there's no lag or queue.
No API costs, no rate limits, no premium paywall. The AI Moderator is included with SlakBot by default.
You set the sensitivity and which actions the bot takes. From mild (serious violations only) to strict (catches light insults too).
Discord's AutoMod works on fixed word lists. The AI Moderator understands context and tone — including disguised words, sarcasm and subtle threats.
A hybrid detection system that combines multiple signals into one reliable score.
A BERT classifier that understands the tone of a message in 6 languages (EN, NL, FR, DE, ES, IT). Runs entirely on-device.
Hand-built English and Dutch lists of profanity, split into categories (mild, explicit, slurs).
Detects threats like "kys", "kill yourself" or "go die" — regardless of language or spelling.
Hate speech and identity attacks (racism, homophobia, etc.) are automatically given the highest priority.
All signals are combined into one score between 0 and 1. Action is only taken once it crosses your configured threshold.
| Setting | What it does |
|---|---|
| On / Off | Enables or disables the AI Moderator entirely, per server. |
| Sensitivity: Mild | Serious violations only (threshold 0.85). |
| Sensitivity: Normal RECOMMENDED | Balanced — recommended for most servers (threshold 0.70). |
| Sensitivity: Strict | Catches lighter insults too (threshold 0.55). |
| Alert channel | Optional channel where moderators get notified on every AI action. |
| Auto-delete | Removes messages immediately on high severity. |
| Auto-warn | Gives the user a warning + a chat message (disappears after 10 sec). |
Go to the SlakBot Dashboard → Moderation → 🧠 AI Moderator
Flip the switch to ON
Choose your sensitivity (Mild / Normal / Strict)
Optionally set an alert channel for your moderators
Click Save — done! The AI Moderator now protects your server automatically.
No. All analysis happens locally on our own servers. Nothing is shared with Google, OpenAI or any other party.
Yes. The system detects toxicity in both English and Dutch — plus four other languages (French, German, Spanish, Italian).
No, it's completely free, included with SlakBot. No API costs, no rate limits, no premium paywall.
Yes. You decide whether messages are deleted, whether the user gets a warning, and whether moderators receive an alert.
On the "Normal" setting the system is balanced. If you do see incorrect detections, you can switch the sensitivity to "Mild".
Add SlakBot and turn on the AI Moderator in your dashboard. No credit card, no external AI, no hassle.