ktg-one/context
C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a receiving model can reconstruct the original context with near-perfect fidelity.
GitHub repository with 32 stars and 4 forks.
Topics: agent-skills, ai-memory, claude-skills, context-engineering