Guardrails
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
ai-securityanomaly-detectiondefensive-tools+3
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
huzjie/aegisagentRuntime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…
owasp/securemlSecureML - Securing and Watermarking AL models
thodoristsampouris/agentguardZero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…
backbay-labs/clawdstrikePolicy engine and EDR for AI agent fleets and developer workstations. Monitors tool calls, file access, network flows, and process execution with…
duriantaco/ravageEvidence first autonomous web security testing for controlled, authorized targets. With reproducible labs, audit trails, reports, and XBEN…
bkuan001/halo-recordTamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.