跳到正文
OpenRouter· @OpenRouter · X·· 2 小时前AI 评分53
AI 导读

OpenRouter 发布 beta 版 Armor,用于在智能体执行工具调用前拦截违反策略的调用。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