Deterministic security solution for AI agents – OpenClaw and 2 more
Deterministic policy engine blocks agent actions without relying on fragile LLM guardrails.
UI refresh on a security wrapper that lacks clear differentiation.
Security engineers deploying AI agents
Guardrails AI · Lakera · Rebuff
What changed? - Complete UI redesign: now the frontend UI looks modern, more organized and intuitive. what we had before was just a raw UI to allow the focus on the back end.
Quick Presentation: Agent Ruler is a reference monitor with confinement for AI agent workflow. This solution propose a framework/workflow that features a security/safety layer outside the agent's internal guardrails. This goal is make the use of AI agent safer and more secure for the users independently of the model used. Currently it supports Openclaw, Claude Code and OpenCode as well as TailScale network and telegram channel (for OpenClaw it uses the built-in telegram channel)
Feel free to get it and experiment with it, GitHub link below
I would love to hear some feedbacks especially security ones.
Note: it has demo video&images on the GitHub in the showcase section
Deterministic policy engine blocks agent actions without relying on fragile LLM guardrails.
Detects AI agents reading secrets without wrapping your workflow unlike Little Snitch.
GitHub-native agent workflow is clever, but AI-maintained sites already exist.
Applies formal verification to prevent prompt injection before any tool executes.
MCP wrapper for SafeDep; valuable but depends entirely on Agentic Workflow adoption.
1,200 security rules for AI agents when OWASP Agentic Top 10 just dropped.