
aegisagent
Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…
ai-securityanomaly-detectionapi-security+4

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…
Open-source sandboxed runtime for AI agents — gVisor/Docker isolation, credential vault, immutable audit log. Built after CVE-2026-25253.

Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…