OpenRouter launches Armor beta to block out-of-policy tool calls
OpenRouter announced the beta launch of OpenRouter Armor, which uses TypeSafeAI's Jev model to guard against out-of-policy tool calls before an agent executes them; OpenRouter says regex-based filtering often isn't enough to detect unwanted tool calls. The company describes Armor as an "auto" permissions mode similar to Claude Code's Auto that works with any model or agent, and says that on an internal test set it generated, Jev 1.13 had the highest accuracy and lowest cost compared with other decision models and Claude Code's use of Sonnet 5. Those performance and cost comparisons are vendor claims and have not been independently replicated.
OpenRouter says regex filtering is often insufficient for catching unwanted tool calls; Armor instead uses a model to judge and block out-of-policy calls before an agent executes them.
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
00:00