Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.
agentguardx added to PyPI
The PyPI repository added 'agentguardx', a runtime security tool for AI agents that inspects, controls, and audits tool calls. AI/ML developers and organizations integrating AI agents into pipelines are affected by potential unchecked tool calls leading to unauthorized actions or data exfiltration.