chancelu/dsh-llmwiki

Name: chancelu/dsh-llmwiki
Author: chancelu

插件Plugin 原生Native ⭐ 2 MIT cat_label.agent-memorycat_label.agent-memory cat_label.deepseek-harnesscat_label.deepseek-harness cat_label.deepseek-harness-plugincat_label.deepseek-harness-plugin cat_label.deepseek-harness-plugin-devcat_label.deepseek-harness-plugin-dev cat_label.deepseek-harness-pluginscat_label.deepseek-harness-plugins

本地Markdown wiki作为DeepSeek Harness的长期记忆——RRF融合检索（关键词+wikilink图+时间维度），令牌预算注入，自动捕获。从llmwiki移植而来。

项目介绍Project Overview

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

dsh-llmwiki 是 DeepSeek Harness 的长期记忆插件，基于本地 Markdown 知识库。它通过关键词、wikilink 图谱与时间检索融合 RRF，在每轮注入相关上下文，并提供 memory_search、memory_save 工具及自动日志。适合需要跨会话记忆、可用 Obsidian 整理笔记的场景。注意：ripgrep/SQLite FTS 与 LLM 自动整理尚未移植。

dsh-llmwiki is a DeepSeek Harness plugin that adds long-term memory using a local Markdown vault. It injects relevant wiki context per turn, registers memory_search and memory_save tools, and auto-captures sessions to daily logs, using keyword, wikilink-graph, and temporal retrieval fused by RRF under a token budget. Use it for cross-session recall and Obsidian-curated notes. Caveat: ripgrep/SQLite FTS and LLM curation are not yet ported.

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-llmwiki】【https://github.com/chancelu/dsh-llmwiki】

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 dsh-llmwiki

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

READMEREADME

3.9 KB · 缓存于 2026-08-27 05:42:00 · 3.9 KB

dsh-llmwiki

Context Window = RAM, Local Wiki = Disk — long-term memory for DeepSeek Harness, powered by your local Markdown vault.

TypeScript port of llmwiki (Python: llmwiki-harness on PyPI), packaged as a native dsh plugin.

What it does

Mechanism	dsh extension point
Inject relevant wiki knowledge into the same turn's model request	`session/event` (`agent/inbox/spliced`, pre-assembly live event) → `ctx.systemPrompt.context()`
Teach the model about memory	`ctx.systemPrompt.section()`
`memory_search` — model recalls prior sessions / curated notes	`ctx.tools.register()`
`memory_save` — model persists durable insights	`ctx.tools.register()`
Auto-capture every turn to `chronicle/daily/YYYY-MM-DD.md`	`session/event` (`turn/end`)

Retrieval: keyword + wikilink graph + temporal strategies fused with RRF (Reciprocal Rank Fusion), assembled under a token budget, with an LRU + TTL cache. Zero runtime dependencies beyond Node.js.

Vault layout (created automatically)

my-vault/
├── raw/               # Layer 1: session dumps
├── chronicle/daily/   # Layer 2: auto-captured daily logs
├── entities/          # Layer 3: compiled knowledge
├── concepts/
├── comparisons/
├── projects/
└── queries/

Open it with Obsidian, curate Layer-3 notes with [[wikilinks]] — the graph strategy follows them.

Install

Requires Node.js ≥ 22 (same as dsh itself) and a working dsh CLI (npm install -g @deepseek-ai/dsh) with pnpm on PATH.

# from npm
dsh plugin --profile web add dsh-llmwiki

# or from a tarball
dsh plugin --profile web add ./dsh-llmwiki-0.1.1.tgz

# verify the layer, then boot
dsh --profile web --dump-config   # shows a "# == dsh-llmwiki" layer
dsh web                           # logs: [dsh-llmwiki] memory plugin loaded, vault: ...

The package declares dsh.bundle, so dsh plugin add activates it automatically — no manual patching needed.

Configure

The plugin works zero-config (vault defaults to ~/llmwiki-vault). To override, add a row to your profile's cordis.patch.yml (or a --patch overlay) — note the override restates the row by id without insert:

- id: llmwiki
  config:
    vaultPath: /path/to/your/vault   # Obsidian vault welcome
    tokenBudget: 2000
    strategies: [keyword, graph, temporal]
    daysBack: 7
    topK: 5
    autoInject: true
    autoCapture: true

A patch replaces the row's entire config, so restate every key you want to keep.

Config

Key	Default	Meaning
`vaultPath`	`~/llmwiki-vault`	Markdown vault path; structure created if missing
`tokenBudget`	`2000`	Max tokens of injected wiki context
`strategies`	`[keyword, graph, temporal]`	Enabled recall strategies
`daysBack`	`7`	Temporal look-back window
`topK`	`5`	Results per retrieval
`priority`	`relevance`	Assembly priority: `relevance` / `recency` / `diversity` / `structured`
`cacheTtl`	`300`	Cache TTL seconds
`autoInject`	`true`	Inject wiki context on each user message
`autoCapture`	`true`	Append each turn to the daily chronicle

How the pieces map from the Python original

Python (`llmwiki`)	TypeScript (`dsh-llmwiki`)
`core/retriever.py`	`src/retriever.ts`
`core/assembler.py`	`src/assembler.ts`
`core/cache.py`	`src/cache.ts`
`vault/capture.py`	`src/capture.ts`
`search/python_engine.py`	merged into `retriever.ts` (keeps the package zero-dep)
`OpenClawMemoryHook` adapter	the dsh plugin itself (`src/index.ts`)

Not yet ported: ripgrep / SQLite FTS engines (the pure-JS engine keeps installs dependency-free — contributions welcome), the LLM-driven curate pipeline (run the Python CLI alongside for now).

License

MIT

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

命令行安装CLI Install 复制安装命令Copy Install