Gives ChatGPT and other remote AI clients long-term memory you can search, inspect, and delete. Deploys to Cloudflare's free tier using Workers, D1, R2, Vectorize, and Workers AI for embeddings, so no VM or database admin needed. Exposes MemPalace-style tools for storing context in drawers, diaries, and knowledge graphs, with semantic search over chunked content. OAuth 2.1 with PKCE handles authorization, and everything is tenant-scoped with quota guardrails. Reach for this when you want continuity across ChatGPT sessions or coding agents that need to remember project decisions, but you want the memory layer remote and self-hosted instead of locked into a provider's black box.