A security scanner for your LLM agentic workflows

Security testing that runs inside the coding agent you already use. Source-available, not open source.

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.

Open-source AI security scanner for Codex, Claude Code, and ACP-compatible coding agents—kept current with OpenAI Codex Security.

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.)