9 packages found
Zero-dependency CLI to scan, recommend, deduplicate, audit, and visualize Claude Code / Codex skills and MCP servers.
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f