OpenRouter 发布 Armor 工具调用防护
SO FKIN COOL
OpenRouter 宣布推出测试版 Armor，用 @typesafeai 的 Jev 模型在智能体执行工具调用前拦截违规调用，官方称性能优于 Claude Code 的自动分类器且成本更低。Diogo Almeida 转发并评论：“SO FKIN COOL”。
查看原帖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…
展开完整原文
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.
正文
当前显示原文，中文全文译文尚未就绪。
SO FKIN COOL