dsh-memo
Memo — session memory search for DeepSeek Harness agents: cross-session full-text recall (memo_search), distilled notes (memo_remember), and corpus stats (memo_stats) over the official sessionQuery service. Zero infrastructure, local-first.
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。
インストール
検証済み bundle がないか、互換性チェックに失敗しています。先にリポジトリの説明を読んでください。 README 全文を読む ↗
ドキュメント
README 全文を読む ↗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.