Siddhant-K-code/distill

Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.

语言：Go · GitHub 星标：198 · Fork：20

话题：ai-agents · anthropic · compression · context-optimization · deduplication · deterministic · developer-tools · go

在 GitHub 上查看原仓库