Crust
ActiveDescription
Open source AI agent security infrastructure that intercepts and blocks dangerous agent behaviors before they happen. Deploy with a single command for real-time behavior monitoring and protection.
Related Projects
NeMo Guardrails
6.1k · Python
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational systems, supporting topic control, safety enforcement, and dialog guidance.
guardrailsllm-safetynvidia +2
AgentGuard
100 · Python
A+ Grade AI Agent Security Framework with military-grade protection against prompt injection, command injection, and Unicode bypass attacks.
agent-securityprompt-injectioncommand-injection +2
Agentic AI Security Starter Kit
13 · Python
Working code examples to defend against Agentic AI threats including prompt injection detection, Claude Code security configuration, and agent access control.
agent-securityprompt-injectionaccess-control +2
ToolTrust Scanner
15 · Go
Security scanner for AI agent tool definitions that detects security vulnerabilities and configuration risks in agent tool interfaces.
agent-securitytool-scanningvulnerability-detection +1