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

Authorized security testing workspace. v2 TypeScript terminal product on release; v1 Python on pypi-release; Go branch is demo only.

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

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

A fast, keyboard-driven HTTP intercepting proxy and hacking & pentesting toolkit for the terminal.

A security scanner for your LLM agentic workflows

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

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

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

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README