eugene1g/agent-safehouse

Sandbox your local AI agents so they can read/write only what they need

What it solves

它为在 macOS 上运行的 LLM 编码代理提供了一个安全层，防止它们访问不需要的敏感文件或系统集成。它解决了代理可能无意或有意地访问其指定工作区之外的私有数据风险。

How it works

Safehouse 使用 sandbox-exec 来实现 "deny-first" 安全模型。它采用可组合的策略配置文件，首先通过封锁所有访问，然后明确地仅允许必要的路径和权限。

它还处理 macOS 特有的路径解析（例如 /etc 中的符号链接）并能自动检测 Git worktrees 以确保代理可以获得所需的元数据访问权限，而不会危害系统安全。

Highlights

  • Deny-first approach: Starts with a total block and allows only specific, required access.
  • Composable profiles: Includes pre-built profiles for popular coding agents and app-hosted workflows.
  • macOS integration: Specifically designed for macOS using sandbox-exec and handles system path resolution.
  • Flexible overrides: Supports machine-specific local overrides and the ability to add read-ityx directories via command-line flags.