Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-expmem
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:mengxiaoxian/lookover#path:/dsh-expmem
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
保存问题、解决做法、来源与适用条件，下次相似任务可检索复用；过时或不准确的经验可以纠正、失效或删除。
属于 lookover 桌面助手组合：dsh-bubble 提供工作页面旁的入口，dsh-look 提供现场上下文，本插件保留可复用经验。也可单独使用，来源来自粘贴文本或文件。
第一次怎么用
任务解决并确认结果后说：
把这次问题、尝试过的办法、最后的解决方法、来源和适用条件保存为经验。没有确认的结果标为未知。
下次遇到相似任务说：
先检索之前关于这个问题的经验，说明当时的适用条件，再判断这次能不能复用。
也可要求“列出已保存的经验”“这条经验已不适用，标记失效”或“删除这个案例及关联经验”。Agent 调用后获得案例 ID，可按 ID 定位；口头要求不等于已执行，应查看工具结果。
保存与复用
| 工具 | 用途 |
|---|---|
mem_save_case |
保存问题、约束、尝试、选择、理由、结果状态与来源，导出可读卡片 |
mem_add_claim |
补充结论和适用条件；未确认时标为推断或待定 |
mem_recall |
检索旧案例，返回来源、条件和相关理由 |
mem_correct |
忽略、失效、删除或恢复；删除案例级联关联经验 |
mem_list |
列出已保存案例 |
插件提供工具与系统提示，由宿主 Agent 结构化信息，不另起模型服务。第一步前的词元召回达到阈值时会提供旧案例；命中和正确引用都不保证，明确请求检索更容易核对。
安装与数据
0.1.1 的宿主声明为官方 DeepSeek Harness 0.2.0-rc.2；组合验证范围为 macOS arm64。关闭 DSH 后安装，再打开：
dsh plugin --profile desktop add https://github.com/mengxiaoxian/lookover/releases/download/lookover-2026.10.12/dsh-expmem-0.1.1.tgz
无 dsh 命令时见官方内置 CLI 用法。
数据默认在 $DSH_HOME/mem（未设置时 ~/.dsh/mem），MEM_DIR 可指定独立目录。结构化记录为 JSONL（逐行 JSON），可读卡片在 cases/<id>.md。卸载不自动清空数据，无云端同步；Agent 引用召回内容时，云端模型仍可能收到相关文本。
当前限制
- 词元打分而非向量语义检索，同义改写可能漏召回。
- 相同结论只做同文去重，自动召回阈值仍需校准。
- 单用户、单进程写入假设，没有并发写锁。
- 复用次数包含自动注入，不等于实际采纳次数。
- 删除更新当前索引和案例卡，追加日志保留历史；不是安全擦除。彻底清除敏感内容需要处理存储目录和备份。
- 存储与工具验证使用模拟资料，不代表任意应用的全自动保存与召回已验收。
npm run demo 在包内 demo/data 创建模拟资料，运行前清空该模拟目录，不接触日常经验目录。早期需求与实验见 ../docs/，不作为新增能力承诺。
Links
More in this category
vectorize-io/hindsight#coding-agents★ 59457
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
volcengine/OpenViking#examples/dsh-memory-plugin★ 41708
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
MemTensor/MemOS#memos-local-plugin★ 12306
Local-first memory plugin for DeepSeek Harness: layered L1/L2/L3 memory with automatic capture, manual memos_* retrieval tools, and a built-in memory viewer.
agentscope-ai/ReMe#dsh★ 3762
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
zilliztech/memsearch#MemSearch★ 2826
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
vshulcz/deja-vu#extensions/dsh★ 1422
Reads the session files forty-two other coding agents on this machine already wrote (Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more), including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.