Aegis
ActiveDescription
Runtime policy enforcement for AI agents with cryptographic audit trail, human-in-the-loop approvals, and kill switch. Zero code changes required.
Related Projects
Cordum
475 · Go
The open agent control plane that governs autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and more.
governanceagent-controlpolicy-enforcement +2
CyberClaw
200 · Python
Next-gen transparent agent architecture with full behavior audit, two-phase secure invocation, dual-level memory, and heartbeat tasks. Compatible with OpenClaw and Claude Code.
transparent-agentauditsafety +2
0DIN Sidekick
27 · JavaScript
Firefox/Chromium extension for AI security researchers that streamlines LLM jailbreak testing and vulnerability discovery across multiple providers.
ai-safetyred-teamingjailbreak +2
HexStrike AI
8.7k · Python
HexStrike AI is an advanced MCP server that lets AI agents autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, and security research.
cybersecuritypentestingmcp-server +2