LLM-supervised persistent memory for AI agents.
功能特性
- Zero user-side operation — install once; supported runtimes can use hooks, minimal runtimes can use persistent rules
- LLM-supervised — the host LLM decides what to remember, update, and forget; no embedded LLM, no API keys
- Runtime-native integration — runtime-specific SKILL.md, shared guide.md, and supported hooks or extensions
- Four-graph architecture — temporal, entity, causal, and semantic edges, not just vector similarity
- Intent-native protocol — three primitives (remember, link, recall) map to the LLM's cognitive vocabulary, not database syntax; structured JSON output with signal transparency
- Intent-aware recall — graph traversal + optional vector search (RRF fusion), enabled by default for all queries
安装命令
dsh plugin --profile web add dsh-mnemon项目预览
项目简介
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.