Aggregate management is equally significant for both streaming and query workloads. However, the prevalent approach of separating stream processing and query analysis impairs performance, hinders aggregate reuse, increases resource demands, and lowers data freshness. μWheel addresses this problem by unifying aggregate management needs within a single system optimized for continuous event streams. μWheel pre-aggregates and indexes timestamped data arriving out-of-order, enabling the sharing of aggregates across arbitrary time intervals while respecting low watermarks. Our performance analysis demonstrates that μWheel dramatically outperforms current aggregate sharing techniques for high-volume streaming, particularly when handling numerous concurrent window slides. Crucially, μWheel also delivers performance comparable to specialized pre-aggregation indexes for supporting ad-hoc queries and does so with significantly reduced storage requirements. μWheel's efficiency stems from its compact wheel-based data layout, featuring implicit timestamps, a query-agnostic time hierarchy, and a query optimizer designed to minimize aggregate operations.