qwert702/dsh-memory

Name: qwert702/dsh-memory
Author: qwert702

插件Plugin 原生Native ⭐ 2 cat_label.conversationcat_label.conversation cat_label.deepseekcat_label.deepseek cat_label.deepseek-harnesscat_label.deepseek-harness cat_label.dshcat_label.dsh cat_label.long-termcat_label.long-term 记忆Memory

Long-term memory for the DeepSeek Harness Web GUI: project-scoped + global memory stores with automatic extraction, automatic briefing injection, small-model periodic consolidation, and an Obsidian-style memory graph.

catalog 简介 / catalog descriptioncatalog description：Long-term memory plugin for the DeepSeek Harness Web GUI: project+global stores, auto extraction/injection, small-model consolidation, Obsidian-style link graph.

项目介绍Project Overview

由知微Agent(zhiwei)编辑Edited by Zhiwei Agent (zhiwei)

dsh-memory 是 DeepSeek Harness Web GUI 的长期记忆插件，提供项目与全局两级 JSON 记忆库，支持对话结束后自动抽取、按新鲜度/强化度/关联度注入 top-K 上下文、定期由小模型合并链接归档，并带记忆列表与图谱视图。适合需要跨会话保留事实、偏好和项目背景时使用；自动抽取/整理依赖模型调用，连续失败会暂停，需手动运行恢复。

dsh-memory is a long-term memory plugin for the DeepSeek Harness Web GUI. It maintains project-scoped and global JSON stores, automatically extracts memories after turns, injects top-ranked memories into system prompts, periodically consolidates them with a model, and provides a searchable list plus Obsidian-style graph. Use it to preserve facts and context across sessions. Extraction and consolidation depend on model calls; repeated failures pause auto-extraction until a manual run succeeds.

在 GitHub 查看View on GitHub

发给你的 DSH 安装Send to your DSH

请帮我了解并安装插件：【dsh-memory】【https://github.com/qwert702/dsh-memory】

把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.

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

命令行安装CLI Install

dsh plugin --profile web add github:qwert702/dsh-memory

把 qwert702/dsh-memory 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.0 KB · 缓存于 2026-08-27 05:41:40 · 3.0 KB

dsh-memory

See README.zh.md for the full Chinese documentation.

Highlights

Two scopes: per-workspace project memories (keyed by a hash of the session cwd) plus one global store; plain JSON under ~/.dsh/memory/ (respects $DSH_HOME), atomic writes.
Memory view tab beside Chat/Trajectory: one-card-per-row list (type dot, tags, origin, reinforcement count, links) with inline edit/archive/link/delete, search, and a canvas force-directed graph with zoom/pan/drag, neighbor highlighting and a detail card.
Auto injection: a global system-prompt/assemble waterfall listener appends the top-K memories (freshness x reinforcement x degree, interleaved scopes, char-capped) as a dynamic context; agentless assemblies get globals only; failures never touch the assembly.
Auto extraction: on turn/end, new events are replayed as a transcript and distilled by the model into JSON candidates; near-duplicates (bigram Jaccard >= 0.65) reinforce instead of duplicating; 3 consecutive failures pause auto-extraction until a manual run recovers.
Periodic consolidation: every N extracted turns per scope (default 20) or on manual trigger, the model proposes merge/link/archive/retag ops that are id-validated and applied transactionally.

Install

dsh plugin --profile web add <repo-or-local-path>
dsh web   # restart, then refresh the page

Settings (`~/.dsh/settings.yaml`)

dsh-memory:
  enabled: true
  injectEnabled: true
  autoExtract: true
  extractProvider: ''   # pair with extractModel to pin a small model
  extractModel: ''
  manageProvider: ''    # consolidation model provider (empty = fall back to extract*)
  manageModel: ''
  consolidateEveryTurns: 20
  topK: 8
  maxInjectChars: 1500
  maxInputChars: 12000
  maxTokens: 1024
  autoArchiveDays: 90       # heuristic auto-archive age in days (0 = off)
  memoryLocale: ''          # force memory language: '' = follow the conversation, or zh/en
  embeddingsEnabled: true   # local semantic embeddings (needs the optional dependency)
  embeddingRemoteHost: ''   # HuggingFace mirror, e.g. https://hf-mirror.com
  autoLinkThreshold: 0.78   # cosine threshold for auto-linking during consolidation (0 = off)

Layout

lib/index.js — host half: settings, injection/extraction listeners, consolidation pipeline, routes.
lib/store.js — two-scope JSON store + durable cursors/counters.
lib/util.js — pure helpers (scope keys, similarity, parsers, transcript builder).
lib/embeddings.js — optional local embeddings (transformers.js WASM): vector sidecar + serial inference queue.
lib/client.js — browser half (hand-written bundle): additive conversation.view entry.
test/smoke.cjs — node test/smoke.cjs.
test/e2e-flow.cjs — six-stage end-to-end business flow (node test/e2e-flow.cjs).

MIT

渲染基于仓库 qwert702/dsh-memory 的 README.md。在 GitHub 查看原文 →

命令行安装CLI Install 复制安装命令Copy Install