OpenRouter· X：OpenRouter (@OpenRouter)·· 3 小时前AI 评分58
OpenRouter 推出 Armor 测试版，拦截智能体的越界工具调用
OpenRouter 推出 Armor 测试版
AI 导读
OpenRouter 发布 Armor 测试版，用于在智能体执行工具调用前拦截不符合策略的调用。Armor 使用 typesafeai 的 Jev 模型做防护，官方称其表现优于 Claude Code 的自动分类器，且成本只是后者的一小部分。
正文
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.
来源：OpenRouter · x.com