给编码 Agent 用的运行时主机沙箱，按每个动作征求授权
Structured execution boundaries and failure reports for PocketMine-MP plugin flows.
Runtime budgets and automatic cancellation companion for pi-subagents
Continuous runtime guard and egress network firewall for securing AI agent execution.
Runtime defense toolkit against prompt injection for LLM APIs — intercepts, analyzes, and protects prompts in real-time
agent-gorgon (formerly agent-warden) is a runtime policy guard for autonomous AI agents that enforces kill/flag policy on a live agent process and emits a forensic report of what it did. Scores file, network, and subprocess behavior against a YAML policy and halts or SIGKILLs the agent before it breaks things. pip install agent-gorgon
Add a description, image, and links to the runtime-guard topic page so that developers can more easily learn about it.
To associate your repository with the runtime-guard topic, visit your repo's landing page and select "manage topics."