OpenRouter launches Armor beta to screen agent tool calls

Image: Primary

Published Friday, October 16, 2026 · 12:10 AM EDT

OpenRouter says it has launched Armor in beta to check whether an AI agent's tool calls violate policy before execution. The service uses Typesafe AI's Jev model to screen those actions. OpenRouter claims better performance than Claude Code's automatic classifier at a fraction of the cost.

Sources

OpenRouter (@OpenRouter)

In this story

Anthropic

Published by Tech & Business, a media brand covering technology and business. This story was sourced from OpenRouter (@OpenRouter) and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

AI Science

Study finds cheaper claim verification carries higher unsupported-claim acceptance

Researchers report in a preprint that combining a cheaper claim verifier with a frontier language model scored 74.10 at USD 2.92 per thousand claims, against 73.83 at USD 8.93 for the frontier model alone. The system sends some cl...

AI Science

Researchers report lower-cost training for LLM information gathering

Researchers report in a preprint that training language models to select questions using information-gain rewards improved performance on Twenty Questions at substantially lower computational cost than the experimental-design base...

Science Security

Researchers report 66 faults in six software security testing tools

Researchers report that LLM4SAST, a framework for testing software security scanners, identified 66 unique faults across six tools. Developers confirmed or fixed 32 after receiving reports, according to the arXiv preprint. The fr...

Science

Researchers report lower quantum circuit resource needs with LLM-guided search

Researchers report in an arXiv preprint that a search framework using large language models discovered quantum circuits requiring fewer Toffoli gates and qubits than prior designs in seven of eight tasks. The models propose circui...

Security AI

AWS says security agent exploited intended flaws in 33 of 37 tests

AWS said its autonomous penetration-testing agent exploited the intended vulnerabilities in 33 of 37 tests involving recently disclosed software flaws. The agent started with an endpoint and minimal information, without an exploit...

AI Security

Researchers find Meta's Muse builds hourly profiles of users' contacts

Security researchers who extracted Meta's Muse operating instructions found a process that compiles and updates profiles of people in a user's life every hour, The Verge reported. The profiles track relationships and inform person...