killertcell428/aigis

Intent-based security plugin for Claude Code - registers a plan per prompt and enforces policy on every tool call via hooks.

Runtime security for AI agents: discover agents, map their permissions, and enforce what they can do.

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segregation of duties, and cryptographically signed, offline-verifiable audit logs.

OpenClaw Security Vault — Atomic "claw" control: every AI reach, within your sight.

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

The control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks, 4,000+ adversarial payloads. Discover. Assess. Test. Monitor. Comply.

ArmorIQ intent enforcement plugin for OpenClaw AI agents