Original Summary

Hi everyone.<p>TypeSafe released Jev last week, and it pushed me to build agent-chaperone. It is a screening layer for AI agent tool calls and tool results.<p>It screens risky, off-task, or secret-leaking actions before they run, and prompt injections or other suspicious instructions before the agent reads them.<p>Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;agent-chaperone&#x2F;agent-chaperone" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;agent-chaperone&#x2F;agent-chaperone</a><p>Website: <a href="https:&#x2F;&#x2F;agentchaperone.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;agentchaperone.dev&#x2F;</a>

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/22 00:34:27