3 projects
securityagent-core
Local-first DLP engine and security layer for AI coding agents. Secures Copilot, Claude Code, Cursor, Windsurf, and any MCP-compatible agent.
agnostic-security
The firewall for AI coding agents — prevents secrets, PII, and credentials from leaking through Copilot, Claude Code, Cursor, and LangChain
breach-intel-client
Python SDK for the Breach Intel Policy Agent — attach any AI agent to breach logging in one import
