NattoCB/dsh-plugin-memory

README 摘要

@deepseek-ai/dsh-plugin-memory English 中文 Persistent five-layer memory for DeepSeek Harness: profile, project context, daily log, and recallable topics — so the agent remembers you across sessions, not just within one. Two cordis seams — agent/pre-step injection + ctx.tools.register (six tools) A persistent five-layer memory system for DeepSeek Harness (DSH): a user profile (L1), a per-project semantic index with topic files (L2), and append-only per-day logs (L3) under /.dsh/memory/ and /.dsh/memory/ . It injects relevant memories into every request and auto-extracts durable facts from finished sessions via the LLM. Integrates as a DSH plugin on two cordis seams — agent/pre-step for injection, ctx.tools.register for six memory agent tools. Without an llm route it still works: entry injection, keyword relevance, and profile rotation remain; only LLM ranking and auto-extraction are disabled. ✨ Features - 🧠 Five-layer model : L0 user-owned identity ( /.dsh/AGENTS.md , not managed by the plugin) → L1 profile → L2 project index + topics → L3 per-day append-only log → L4 skills (existing). Each layer has its own write path, truncation budget, and injection rule. - 📇 Index + topic spli…

分类