前端请求治理平台 —— 拥有多重能力,支持自由组合的一站式请求守护方案
A two-tier async cache with SQLite persistence, in-memory pseudo-LRU, stale-while-revalidate, cross-thread deduplication via SharedArrayBuffer , and automatic request coalescing.
MemWeave local-first memory infrastructure for AI agents: structured memory, 4-layer retrieval (BM25 + vector + graph + causal), token-budgeted injection, server-side write deduplication, and background consolidation. Server process: Fastify REST API + CL
Centralised geolocation controller with TTL caching and request deduplication