OpenRouter 发布 Armor 测试版，拦截智能体越权工具调用
Today, we are launching OpenRouter Armor in beta.
AI 导读
OpenRouter 推出测试版 Armor，在智能体执行工具调用前拦截不符合策略的调用，用于弥补正则过滤的不足。Armor 使用 typesafeai 的 Jev 模型，官方称其表现优于 Claude Code 的自动分类器且成本更低。Armor 还让 Claude Code 的自动权限模式可兼容任意模型，可通过 Ori 运行，例如 ori claude --model moonshotai/kimi-k3 -- --permission-mode auto。
正文
当前显示原文，中文全文译文尚未就绪。
Today, we are launching OpenRouter Armor in beta.
Tool calls allow agents to interact with the world, and regex-based filtering often isn't enough to detect unwanted tool calls.
Armor uses @typesafeai's Jev model to guard against out of policy tool calls before your agent executes them, with better performance than Claude Code's auto classifier at a fraction of the cost.