Skip to content
OpenRouter Blog·Indexed by this site · Originally publishedSelectedAttention39

OpenRouter launched the Armor beta, intercepting agent rule-violating tool calls before execution

AI summary

OpenRouter launched the Armor beta, inserting a classifier between the model and the user's application that judges each model tool call before deciding whether to allow or block it. Rules are written in natural language in plain English, divided into hard_deny, soft_deny, and allow categories; calls hitting hard_deny are always blocked and cannot be allowed, while soft_deny can be lifted by allow rules or explicit user requests in the conversation. Armor implements a Claude Code-compatible API, and when reasoning through OpenRouter's Ori metaharness, enabling Claude Code auto mode requires no additional configuration; blocked calls are returned to the model with the triggering rule, and the model rewrites the call or explains to the user.

Why it was selected

OpenRouter publicly detailed Armor's mechanism and latency cost of judging with natural language rules before tool calls, which can serve as a reference for building your own agent guardrails.

Read originalopenrouter.ai