Security middleware for AI Agents. Intercepts shell commands before execution using a multi-layer pipeline: binary allowlist, regex patterns, deterministic intent coherence mapping, and LLM semantic check as last resort.

Shield your terminal from AI agents. Aegis intercepts every shell command, auto-snapshots your data before dangerous operations, and asks before anything destructive runs. Works with Claude Code, Codex, Cursor, and any agent that uses $SHELL.

A lightweight Paper library for intercepting Minecraft Brigadier commands at the node level, enabling precise, reliable command control without parsing raw strings or overriding vanilla behavior.