OpenRouter· @OpenRouter · X·· 2 小时前AI 评分49
AI 导读
今天,我们推出 OpenRouter Armor 测试版。 工具调用让智能体能够与外部世界交互,而基于正则表达式的过滤往往不足以检测不受欢迎的工具调用。 Armor 使用 @typesafeai 的 Jev 模型,在你的智能体执行工具调用之前,拦截违反策略的调用,性能优于 Claude Code 的自动分类器,而成本仅为后者的一小部分。
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