Stateless dialogue compression that mimics human memory
Stateless dialogue compression that mimics human memory. LLM conversations stay bounded forever — no session management, no context overflow.
Project overview
MosaicCompress Stateless dialogue compression based on natural forgetting curve.
LLM conversations grow linearly. MosaicCompress keeps them bounded — automatically, invisibly, and without the user ever knowing what a "Session" is. How It Works Steady state: constant message count — 2 + heavyStart × (messages per round), e.g. 102 messages for pure two-message rounds, whether at round 60 or round 15,000 (higher, but still constant, when tool-call rounds add messages). The compression ratio approaches 100%. Philosophy: Alive Memory, Not a Handover Brief
MosaicCompress models the opposite: biological forgetting. A human does not remember round 3 of a 300-round conversation — they keep the lesson, the rules, the relationship. The algorithm reproduces that curve inside one message array: