A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
OpenGuardrails (OGR) Python SDK — the openguardrails core runtime. Agent/sandbox instrumentation lives in its own repo: openguardrails-instrumentation-hermes (Hermes + srt/OpenShell).
Runtime Gateway for AI Agents. 17-phase security pipeline between agents and LLM APIs. Works with OpenClaw, Paperclip, Claude Code, Cursor. Open source, MIT license.
Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.
