dsh-memo
Memo — 专为 DSH 设计的本地跨会话记忆搜索与知识提炼工具。
AI 分析
核心用途是让 Agent 能够检索历史会话并记录提炼后的知识。适合需要跨会话保持上下文、希望 Agent 记住个人偏好和历史决策的用户。
安装
此插件尚未提供可验证的 bundle，或兼容性检查未通过。请先阅读仓库说明。 阅读完整 README ↗
说明文档
阅读完整 README ↗Memo
Status: WIP (0.0.1 placeholder) — the functional plugin lands in the first release; this package currently reserves the name.
Session memory for DeepSeek Harness agents — built directly on the official sessionQuery service, so every session you ever had is searchable memory:
memo_search(query)— cross-session full-text recall with snippets, titles, and time filtering.memo_remember(text, tags)— distilled notes (decisions, preferences, facts) kept apart from raw logs.memo_stats()— corpus overview: session count, recent titles, note count.
Zero infrastructure, local-first, no vector database. Benchmark targets: LongMemEval-S (retrieval hit@k/MRR), LoCoMo.
License
MIT — see LICENSE.