How zenguard-ai/fast-llm-security-guardrails works
ZenGuard is a small Python client for ZenGuard’s hosted detection API. A caller configures credentials and a service tier, then submits text with one or more detector choices; the client validates the request, selects an endpoint, and returns the API response. The README documents prompt-injection, jailbreak, PII, topic, keyword, and secrets protections, but this repository exposes detector paths rather than implementing their analysis. The graph therefore focuses on the client’s runtime behavior; detector capabilities share the enum that defines their endpoints.
Main entry points: zenguard.py ZenGuard client
Components 5
Other components
- AI application
- Client configuration
zenguard/zenguard.py - ZenGuard client
zenguard/zenguard.py - Detector choices
zenguard/zenguard.py - ZenGuard API
Connections 7
- AI application → Client configuration: provides credentials
README.md - AI application → ZenGuard client: submits prompt
README.md - Client configuration → ZenGuard client: configures tier
zenguard/zenguard.py - AI application → Detector choices: selects detectors
README.md - ZenGuard client → Detector choices: selects endpoint
zenguard/zenguard.py - ZenGuard client → ZenGuard API: posts request
zenguard/zenguard.py - ZenGuard API → ZenGuard client: returns response
zenguard/zenguard.py