OpenRouter launches Armor: LLM-powered guard against out-of-policy agent tool calls
dfinke · x · 2026-10-17
OpenRouter has launched Armor. Tool calls let agents interact with the world, but regex-based filtering isn't enough to detect unwanted tool calls. Armor uses typesafe ai's Jev model to guard against out-of-policy tool calls, adding a security layer for agents in production.
Related event: OpenRouter Launches Armor to Block Unsafe Agent Tool Calls(3 posts)→
More from coding & agent
- Dev spins up full k8s cluster inside sandboxes via new LAN feature, runs agent experiments unattended — willcb · 2026-10-17
- Factory AI makes Delegations generally available for handing work to Droid — matanSF · 2026-10-17
- SandMatter co-founder: a convincing final answer isn't enough to ship an agent — VariousMechanic5811 · 2026-10-17
- Pest-Control Engineer Falls for OpenClaw, Buys Mac Studio Mid-Road-Trip — heyneighbor · 2026-10-17
- Consumer agents creating virtual cards on their own BIN means users lose credit card rewards — km · 2026-10-17
- He's reverse-engineering Grammarly with Perplexity's new REA skill and 10K free credits — ChrisUniverse · 2026-10-17