The AI security agent guards your code.

A security scanner for your LLM agentic workflows

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Open-source adversary emulation for AI agents and MCP servers.

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)