vigilguard/sojka-worker repository overview

Content Safety Model (Polish). Toxicity detection for Polish text.

Vigil Guard Enterprise - AI Detection and Response platform. Real-time security oversight of every AI interaction: prompt injection detection, PII protection, content moderation, semantic drift detection. Deploy on-premises with zero external dependencies.

⚠️ WARNING: Do not install individual Docker images manually. Use the official installer:

curl -fsSL https://get.vigilguard.ai -o /tmp/install.sh && sudo bash /tmp/install.sh

For documentation, support, and installation guide: https://www.vigilguard.ai⁠

⁠sojka-worker

Content safety worker for Polish. Detects harmful content using specialized Polish language model.