Show HN: Armorer – 一种用于 AI 智能体的安全本地控制平面
1 分•作者: cristianleo•3 个月前
嗨，HN，
我开发了 Armorer，因为它让我对两件事感到厌倦：
1. 设置新的 AI 代理（Codex、OpenClaw 等）时遇到的绝对“依赖地狱”。
2. 将强大的本地代理赋予对我的主机广泛访问权限所带来的安全风险。
Armorer 是一个安全的本地控制平面，用于管理您的代理的生命周期。它使用 Docker 实现真正的进程隔离，并提供统一的 UI/CLI 用于监控和作业跟踪。
我特别兴奋的一个功能是：您可以将现有的编码代理指向 Armorer 仓库，它将自动为您安全地安装和配置整个堆栈。
源代码：[https://github.com/ArmorerLabs/Armorer](https://github.com/ArmorerLabs/Armorer)
网站：[https://armorerlabs.com](https://armorerlabs.com)
我很乐意听取您对架构的看法，以及您如何在本地处理代理安全问题。
查看原文
Hey HN,<p>I built Armorer because I was tired of two things:
1. The absolute "dependency hell" of setting up new AI agents (Codex, OpenClaw, etc.).
2. The security risk of giving powerful local agents broad access to my host machine.<p>Armorer is a secure local control plane that manages the lifecycle of your agents. It uses Docker for true process isolation and provides a unified UI/CLI for monitoring and job tracking.<p>One feature I’m particularly excited about: you can point an existing coding agent at the Armorer repo, and it will autonomously install and configure the entire stack for you securely.<p>Source: <a href="https://github.com/ArmorerLabs/Armorer" rel="nofollow">https://github.com/ArmorerLabs/Armorer</a>
Website: <a href="https://armorerlabs.com" rel="nofollow">https://armorerlabs.com</a><p>I’d love to hear your thoughts on the architecture and how you're handling agent security locally.