
Guardrails
Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
ai-securityanomaly-detectiondefensive-tools+3
7.0k

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Open-source security framework for real-time event tracking, threat detection, and risk scoring. Monitors user behavior, detects fraud, bot attacks,…

Real-time malicious traffic detection system using public blacklists, static malware trails, and heuristic analysis to identify threats across DNS,…