Displaying 1 to 21 of 21 repositories
LLM Guard injection detection model (Python). ONNX-based dual-pass classifier detecting prompt injec
13d
1.2K
Presidio PII detection microservice. Provides named entity recognition and pattern-based PII detecti
13d
943
Semantic similarity detection using embeddings and vector store. Detects prompt injection via semant
13d
1.2K
Language detection service using fastText. Detects input language and applies language-specific dete
13d
882
Qdrant vector store persistence container. Maintains embedding vectors for semantic similarity detec
13d
1.5K
Content safety worker for Polish. Detects harmful content using specialized Polish language model.
13d
858
Content safety worker for English. Detects toxic and harmful content using multilingual content mode
13d
824
Scope drift detection worker (Python). Uses semantic embeddings to classify conversation drift from
13d
968
Qdrant vector store initialization. Pre-seeds vector embeddings for semantic detection.
13d
1.3K
Scope drift detection orchestrator. Coordinates semantic analysis to classify prompts as on-topic, n
13d
10K+
Decision arbiter combining signals from multiple detection workers. Applies weighted scoring and bus
13d
816
Backend API for configuration interface. Manages settings, rule sets, policies, and monitoring dashb
13d
899
Public REST API (Express.js) serving detection requests. Handles authentication, rate limiting, mess
13d
950
PII detection worker. Identifies sensitive data (names, emails, credit cards, PESEL, NIP) in prompts
13d
1.1K
Web-based configuration and investigation interface for managing Vigil Guard deployment and reviewin
13d
765
Heuristics-based detection worker. Analyzes prompts using pattern matching and statistical analysis.
13d
1.2K
Asynchronous logging worker. Ingests detection events into analytics database with configurable rete
13d
844
Content moderation orchestrator. Coordinates content safety analysis across multiple language-specif
13d
844
Helper scripts and utilities. Includes stack initialization, health checks, and management tools.
13d
1.7K
NATS integration layer for LLM Guard detection model. Provides request-reply interface to injection
13d
1.1K
SIEM log forwarder. Sends normalized detection events to external security systems via Vector integr
13d
757