GitHubAI Skills, Agents & MCP · Agent safety
Linux command runner with a time limit that guarantees no process an agent's command started survives, using cgroup v2 kill or a subreaper plus pidfds.
Why it’s a gem
Fixes the stray daemon and hung pipe problem that breaks agent and CI runs.
Open-source runtime layer for AI coding agents that intercepts shell, secrets, MCP, and installs locally.
CLI that runs coding agents inside hardware-isolated virtual machines for safe autonomous operation.
Real-time guardrails that detect and block secret leakage in agent output and tool calls.
Hook that intercepts destructive shell commands before an autonomous agent executes them.
Source-linked archive of documented incidents where AI coding agents and chatbots deleted data, leaked secrets or burned money, each with the lesson.
Self-hosted Go sandbox service for agent-written code that reports the isolation tier of every run, refuses runs below a floor and brokers API calls without exposing credentials.