highland0971/dsh-native-memory

DeepSeek Harness的原生按工作区长期记忆:审批门控写入、引用来源、FTS跨会话召回——无需外部服务器,无额外运行时依赖。

Project Overview项目介绍

dsh-native-memory adds per-workspace long-term memory to the DeepSeek Harness. It stores facts and profiles in a dedicated harness storage-domain, supports cross-session recall via session-query FTS, and gates every write behind explicit human approval with cited provenance and a session-log audit. Use it when a project needs durable, workspace-scoped context that survives sessions. Caveat: the plugin runs third-party code with your permissions, so review the source and security model first; secret-shaped text is rejected by default, though the credential detector may flag benign long token-like values.

DSH 原生长记忆插件:每个工作区在 harness 自有存储域中独立保存事实与画像,通过会话查询 FTS 跨会话召回,写入需人工审批并记录出处,工具涵盖记忆、编辑、遗忘、检索、合并、导入、导出与画像读取。当心:插件以你的权限执行第三方代码,请审阅源码与安全模型;默认拒绝写入密钥类文本,但凭证检测可能误判较长的 token 字段。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-native-memory

highland0971/dsh-native-memory 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-native-memory

Awesome DSH Plugin License: MIT

Native, per-workspace long-term memory for DeepSeek Harness (dsh): facts and profiles stored on the harness's own storage-domain, cross-session recall through session-query FTS, approval-gated writes, and cited provenance — no external server, no extra runtime dependency.

⚠️ Installing a plugin runs third-party code on your machine with your own permissions. Review the source (src/) and the security model before installing.

Why this one

dsh-hermes-memory dsh-native-memory
Storage ~/.dsh/settings.yaml namespace dedicated storage-domain unit (~/.dsh/storages/dsh_memory.json)
Scope user-global, all projects per workspace (exact-cwd authorization)
Write safety silent, model-only human approval gate + session-log audit
Recall everything always injected (hard caps) bounded always-on profile plus on-demand recall + FTS over past sessions
Dependencies vendored imports into the harness checkout none beyond zod + the harness itself

See docs/design.md for the full architecture and the competitive landscape analysis.

Install

dsh plugin --profile web add dsh-native-memory   # npm after release
dsh plugin --profile web add /path/to/this/repo  # from a checkout

Restart dsh web. The bundle enables session-query full-text search and adds the memory tools to every session. Details and configuration: docs/install.md.

Tools

Tool Kind Gate
memory_remember add/update a fact in this workspace (secrets rejected by default) approval
memory_edit replace a fact approval
memory_forget archive a fact (soft delete) approval
memory_recall deterministic three-tier keyword scan (tags > text > fuzzy; freshness/access tie-breaks) none
memory_search FTS over this workspace's past sessions (caller excluded) none
memory_expand expand a fact's citation to the original log excerpt none
memory_consolidate near-duplicate merge suggestions + cap budget none
memory_import import candidate facts from a past session's log approval (per fact)
memory_profile read the always-injected workspace profile none
memory_export write a git-friendly Markdown mirror (.dsh-memory/memory.md, masked, idempotent) none

Every fact records its origin (sessionId, seq) — memory stays reconstructable from the lossless session log.

Writes reject secret-shaped text (tokens / keys / passwords) by default; secretPolicy: "mask" | "off" in the bundle patch relaxes that. The credential-assignment detector can flag benign token: … values of ≥16 characters. Prompt injection and tool output always mask secrets.

A read-only browser page (settings → 记忆) lists every workspace's facts with secrets masked; deletions are copied as a memory_forget instruction and land in the chat through the approval gate.

Opt-in session-end proposals (proposeOnSessionEnd: true): one cheap LLM call distills a finished session into candidate facts shown in the next sessions; they become facts only through the approval-gated memory_remember.

A compaction drift guard (compactionGuard: true, on by default) surfaces literal anchors a compaction summary dropped, as data to verify in the next sessions — deterministic, no LLM.

Development

pnpm install
pnpm build && pnpm typecheck && pnpm test

New contributors start at docs/handoff.md and docs/contributing.md. Chinese docs: README.zh.md.

License

MIT

上一个 Prev dsh-shunshun-wallpaper 下一个 Next dsh-think-ultra