Apache-2.0 授權、由 LLM 監督的 AI Agent 持久記憶，透過 dsh-mnemon 外掛接入 DeepSeek Harness，構成受監督的三層記憶系統。
DSH 整合
相容
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
Apache-2.0
01它能幫你完成什麼？
Give DeepSeek Harness agents persistent, cross-session agent memory
Long-term memory spaces in a four-graph knowledge store (temporal, entity, causal, semantic), with intent-aware recall and automatic deduplication
DeepSeek Harness users whose agents lose critical decisions across sessions and need durable knowledge that survives context compaction
Share one pool of agent memory across sessions and frameworks
A single local `~/.mnemon` SQLite database readable and writable by Claude Code, Codex, Cursor, OpenClaw, DeepSeek Harness and other supported runtimes
Teams running multiple agent tools who want cross-session, cross-framework knowledge instead of isolated per-tool memory
02如何將外掛接入 DeepSeek Harness？
先決條件
- The `mnemon` binary installed on the host — via Homebrew Cask (`brew install --cask mnemon-dev/tap/mnemon`), `go install github.com/mnemon-dev/mnemon@latest`, or from source (`make install`)
- DeepSeek Harness (dsh) with the Web profile running
安裝步驟
- 01
Install mnemon on the host: `brew install --cask mnemon-dev/tap/mnemon` (macOS), or `go install github.com/mnemon-dev/mnemon@latest` (macOS / Linux / Windows)
$ brew install --cask mnemon-dev/tap/mnemon
- 02
Add the DSH plugin: `dsh plugin --profile web add dsh-mnemon`
$ dsh plugin --profile web add dsh-mnemon
- 03
Restart your DSH Web profile: `dsh --profile web`
$ dsh --profile web
- 04
Open DSH's Settings → Plugin Config → Mnemon to pick a storage scope, and use the Memory System tab in a session to create or activate memory spaces
驗證整合成功
- `mnemon --version` and `mnemon agency --version` confirm the binary installation
復原
- `mnemon setup --eject` removes all integrations
03DSH 整合程度與能力邊界
Installed as the dsh-mnemon plugin via `dsh plugin --profile web add` after placing the mnemon binary on the host; layers DSH runtime memory, managed project documents and Mnemon long-term memory spaces
Four-graph knowledge store
facts, decisions and insights the host LLM chooses to remember→temporal, entity, causal and semantic edges — not just vector similarity — with importance decay and garbage collection
memory is persisted to a local SQLite database under `~/.mnemon`LLM-supervised memory operations
the host LLM's judgment calls on what to remember, link and recall→structured JSON results from three primitives (`remember`, `link`, `recall`); no embedded LLM, no API keys
`mnemon setup` deploys skill files, hooks and behavioral guides into each runtime's config directoryIntent-aware recall
natural-language recall queries from the agent→graph traversal plus optional vector search (RRF fusion), enabled by default for all queries; `remember` auto-detects duplicates and conflicts
Multi-framework memory sharing
one `~/.mnemon` store→memory shared across Claude Code, Codex, Cursor, TRAE, Qoder, OpenClaw, DeepSeek Harness (via dsh-mnemon) and more; named stores and `MNEMON_STORE` isolate per project
optional local Ollama can be added for enhanced vector+keyword hybrid search
04適合誰？何時不該用？
適合
- DeepSeek Harness users whose agents lose critical decisions across sessions and need durable knowledge that survives context compaction
- Teams running multiple agent tools who want cross-session, cross-framework knowledge instead of isolated per-tool memory
不適合
- Windows supports the core Memory commands, but Agency remains unavailable on Windows until its local authority boundary has native Windows security.
- The DeepSeek Harness integration depends on the separate dsh-mnemon plugin (omdsh-dev/dsh-mnemon), which must be added via the dsh plugin CLI after mnemon is installed on the host.
05相容性、維護與安全提醒
- Windows supports the core Memory commands, but Agency remains unavailable on Windows until its local authority boundary has native Windows security.
- The DeepSeek Harness integration depends on the separate dsh-mnemon plugin (omdsh-dev/dsh-mnemon), which must be added via the dsh plugin CLI after mnemon is installed on the host.
- Mnemon is a young project (repository created 2026-02) still below v1; durable writes go through supervised sub-agents and the storage scope must be picked manually in DSH's plugin config.
Apache-2.0 · actively maintained (latest release v0.2.4, 2026-08-19)
06常見問題
Mnemon 如何接入 DeepSeek Harness？
透過 dsh-mnemon 外掛接入。先在主機安裝 mnemon，接著執行 `dsh plugin --profile web add dsh-mnemon` 並重啟 DSH Web profile；再到 Settings → Plugin Config → Mnemon 選擇儲存範圍，在工作階段中用 Memory System 分頁建立或啟用記憶空間。
Mnemon 是 DSH 原生外掛還是 MCP 伺服器？
都不是。Mnemon 採 LLM 監督模式：一個獨立的本地二進位檔，只提供 `remember`、`link`、`recall` 三個原語，由主機 LLM 決定記什麼、何時遺忘——不內嵌 LLM、不走 MCP、不需 API key。
需要哪些前置條件？
主機上安裝 `mnemon` 二進位檔——可用 Homebrew Cask（`brew install --cask mnemon-dev/tap/mnemon`）、`go install github.com/mnemon-dev/mnemon@latest` 或從原始碼建置——以及執行 Web profile 的 DeepSeek Harness（dsh）。
我的記憶資料存在哪裡？
全部儲存在本地 `~/.mnemon` 下的單一 SQLite 資料庫（可用 `MNEMON_DATA_DIR` 更改位置）；可選的本地 Ollama 能加強向量＋關鍵字混合檢索，資料不會離開你的電腦。
其他 agent 能共用同一份記憶嗎？
可以。預設所有工作階段共用同一個 `default` 儲存，Mnemon 也支援 Claude Code、Codex、Cursor、TRAE、Qoder、OpenClaw 等執行環境；具名儲存與 `MNEMON_STORE` 環境變數可依專案隔離記憶。
07相關的 DSH 工作流程
deepseek-reasonix
作者 esengine
專為 DeepSeek 打造的終端 AI 程式設計智慧體，圍繞字首快取穩定性設計，可常駐執行。
phi
作者 pulseaiclub
來自 pi 的編碼智慧體，支援無限提供方、子智慧體、行內編輯與許可權門控。
sivtr
作者 ariestar
A unified agent memory workspace for human and agent | 一個統一的agent記憶工作空間
baro
作者 jigjoy-ai
把目標自動推進為 Pull Request 的命令列外掛，並提供 Mozaik 執行時沙箱，用於測試併發 AI 程式設計智慧體。
08資料與來源
which layers DSH's runtime memory, managed project documents, and Mnemon's long-term memory spaces into one supervised t…
With `mnemon` installed on the host (see Install), add the plugin and restart your DSH Web profile: `dsh plugin --profil…
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。