Cordum
ActiveDescription
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.
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
ToolEmu
202 · Python
An ICLR 2024 Spotlight LM-based emulation framework for identifying the risks of LM agents with tool use, helping discover safety issues in tool-using agents.
emulationrisk-assessmenttool-use +2
Aegis
353 · TypeScript
Runtime policy enforcement for AI agents with cryptographic audit trail, human-in-the-loop approvals, and kill switch. Zero code changes required.
policy-enforcementaudithuman-in-loop +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