node9-proxy: Node9 is an execution security layer for AI agents that intercepts dangerous shell commands and tool calls in real-time. It features a multi-channel approval system (native popup, browser, Slack, terminal), a flight recorder for live monitoring, and an AI negotiation loop to guide safer behavior. It also includes DLP content scanning and shadow git snapshots for undo.; Auto-claude-code-research-in-sleep: Auto-claude-code-research-in-sleep (ARIS) is a set of custom Claude Code skills for autonomous ML research workflows. It orchestrates cross-model collaboration, with Claude Code executing research tasks and an external LLM (like GPT-5.4) critically reviewing. This system can autonomously discover ideas, run experiments, and write/refine research papers, allowing researchers to wake up to ready-to-submit results.
Protect AI agents from executing dangerous commands during development
Explore new research areas and discover novel ideas through literature surveys and brainstorming.