Research With Anyray, Claude solves more tasks, faster, at 32% lower cost GSYS Gidi SteinbergYarden Shechter Nov 22, 2026 Read moreRead more
Research Why model routing backfires in agent sessions, and what a switch really costs YS Yarden Shechter Nov 11, 2026 Read moreRead more
Research The decision engine: how Anyray learns what is safe to cut GS Gidi Steinberg Nov 8, 2026 Read moreRead more
Research Why context compression breaks prompt caching, and how to keep the prefix stable DRYS Dean RubinYarden Shechter Nov 4, 2026 Read moreRead more
Research How retrieval handles make lossy compression safe YS Yarden Shechter Nov 1, 2026 Read moreRead more
Engineering cacheLint: detect prompt-cache breaks in LLM agents YS Yarden Shechter Oct 28, 2026 Read moreRead more
Engineering Running Claude Code behind an AI gateway: the 200k context trap and the env vars that fix it DR Dima Rudenko Oct 23, 2026 Read moreRead more
Engineering Fail-open by design: how Anyray keeps your traffic flowing when something breaks Anyray team Oct 14, 2026 Read moreRead more
Engineering How Anyray works: cutting tokens before the model without breaking the cache DR Dean Rubin Sep 27, 2026 Read moreRead more