FAQ
Questions, answered.
Is Targa really free?
Yes. The Layer-1 classical engine is CPU-only and costs effectively $0 per message to run, so the free tier is free forever — it isn't a trial. The paid M2 tier adds LLM-grade detection for AI-driven attacks.
How do I add Targa to my group?
Request access at app.targa.dev/register (private beta), then add @targa_bot to your group as an admin and connect the channel from your dashboard.
What does 'explainable' mean in practice?
Every action carries a structured reason. Send /why with the verdict id and you get the verdict, the score, and the exact signals that fired — for example avatar_pHash_matches_admin · join_age<10m · first_message_link.
What kinds of spam does it catch?
Homoglyph-obfuscated text, edit-after-post bypasses, admin impersonation, link/crypto giveaway spam, and flood bursts. The M2 tier extends detection to conversational scam funnels and hyper-personalized phishing.
Will it conflict with my existing moderation bot?
No. Targa focuses on screening messages and members; rule-based moderation bots can run alongside it.
Is Targa open source?
No — closed source, and hosted by us. You don't run infrastructure, and detection internals stay ahead of adversaries.
What data does Targa see?
Messages in groups it protects, as any admin bot does. Verdicts and signals are retained so /why works; see the dashboard's privacy page for specifics.