OpenRouter launches Armor beta to block out-of-policy agent tool calls before execution
dfinke · x · 2026-10-16
- OpenRouter has launched OpenRouter Armor in beta, a safety layer for agent tool calls.
- The problem: tool calls are how agents interact with the real world, and regex-based filtering often fails to catch unwanted calls.
- Armor uses typesafeai's Jev model to block out-of-policy tool calls before the agent executes them.
- OpenRouter claims better detection performance than Claude Code's auto classifier at a fraction of the cost.
Related event: OpenRouter Launches Armor Beta to Guard Agent Tool Calls(2 posts)→
More from coding & agent
- Dev uses Grok to clean up 3D printer firmware, catches it sneaking in nonsense code — yacineMTB · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16
- Yacine: vibe-coded repos with 3,330 agent-written tests are all useless — yacineMTB · 2026-10-16
- Dev argues coding models now beat nearly all engineers in every branch of software — zack_overflow · 2026-10-16
- Q4-quantized coder model on 8-core CPU builds interactive solar system demo in one shot — IntrepidMindExplorer · 2026-10-16