DSH memory plugins: long-term memory for DeepSeek Harness

Concepts & ArchitecturePublished 2026-08-26Author: DSH Plugin Hub
DeepSeek HarnessDSH pluginmemory pluginslong-term memorycross-session memory
DSH memory plugins add cross-session long-term memory to DeepSeek Harness: five real picks compared by feature and install method, plus a step-by-step guide.

DSH memory plugins solve DeepSeek Harness's cross-session amnesia: DSH session state in memory-mode scopes lives only in the process and is lost on restart (confirmed in the official source), so without a memory plugin a new session knows nothing about the old one. Memory plugins persist important facts to local SQLite or files and inject them when a new session starts - the common mechanisms are auto-extraction, auto-injection and context compression. This guide reviews five representative memory plugins from the registry, compares them, and gives selection criteria plus install steps.

Overview

In one sentence: if you want "the AI to remember what you said last time", install a memory plugin. It is not about conversation quality but about persistence - which facts to keep, how to store them, and how to retrieve them in a new session. Below: what the problem is, five representative plugins, then selection criteria and install steps.

What memory plugins solve (cross-session long-term memory)

Cross-session long-term memory is the core value of a memory plugin - without one, a new session knows nothing about the old one. DSH sessions and settings live in different scopes, and in the official source a memory-mode scope only keeps its writes in the process without persisting them (source). In other words, "remembering you" is not reliable by default - a plugin has to write it to disk. Memory plugins share four mechanisms:

  1. Auto-extraction: during a conversation, distill key facts, decisions and preferences.
  2. Auto-injection: at the start of a new session, put relevant past memory into context so the AI "remembers" from the first turn.
  3. Context compression: compress long histories into key points or knowledge structures to save tokens without losing the essentials.
  4. Local persistence: memory is stored in local SQLite or files, no external service, survives restarts.

Memory data lives locally by default - which is why memory plugins commonly advertise "local-first" and "SQLite storage".

Five real memory plugins: picks and comparison

The DSH plugin registry has many memory plugins with different trade-offs - the five below are representatives of different approaches. Data comes from real registry entries (dsh-memento, graph-memory, dsh-meow-memory, dsh-auto-memory, dsh-memory):

PluginCore mechanismInstall methodStatus
dsh-memoryProject+global stores, auto extract/inject, small-model consolidation, Obsidian-style link graphGitHub sourceBasic, early addition
graph-memoryKnowledge graph, cross-session recall, 75% context compression, semantic vector retrieval, local-firstGitHub source (beta, not on npm)v2.0.0, high stars, active
dsh-mementoBounded & layered, unbypassable approval gate, SQLite storage, snapshot injection, rebuildable audit trailnpm one-clickv0.4.5, verified
dsh-auto-memoryThree-layer memory injection, calendar reminders, AI greetings, daily journalnpm one-clickverified
dsh-meow-memorySeven-layer SQLite store, BM25 retrieval, first-turn injection, nightly dream consolidationnpm one-click (package meow-memory)v0.17.0, verified

The approaches are easy to tell apart: graph-memory goes "knowledge graph + vector retrieval" and excels at context compression; dsh-memento goes "approval + audit" so every memory write needs approval and leaves an audit trail - great when you care about control; dsh-meow-memory goes "structured layers + keyword retrieval" and archives memory with nightly "dream consolidation"; dsh-auto-memory goes "fully automatic + humanized", auto-recording and auto-reminding; qwert702's dsh-memory is a general-purpose "dual store + link graph" pick. To browse more, open the memory category in DSH Plugin Hub and sort by stars and compatibility.

How to choose and install

Pick a memory plugin by install method first, then by feature focus - npm one-click suits beginners, GitHub source builds are harder. Four selection criteria:

  1. Check the install method: npm-published plugins (dsh-memento, dsh-meow-memory, dsh-auto-memory) install with one dsh plugin --profile web add <package> command; GitHub-source plugins (graph-memory, qwert702's dsh-memory) use github:owner/repo and can hit missing build artifacts or allowBuilds prompts, which is a higher bar.
  2. Check the feature focus: for control and audit pick dsh-memento (approval gate); for fully automatic pick dsh-auto-memory; for knowledge graph plus compression pick graph-memory; for structured layers plus keyword retrieval pick dsh-meow-memory; for a link-graph organizer pick dsh-memory.
  3. Check compatibility: prefer verified entries in the registry; try unconfirmed ones on a small scale first.
  4. Install one at a time: memory plugins overlap, and running several can double-inject context - get one primary memory plugin working first.

Installing dsh-memento, step by step:

  1. Start the Web UI: run dsh web (same as dsh --profile web) and open http://127.0.0.1:3080 in the browser.
  2. Go to Settings -> Plugin Center (that is DSH Plugin Hub) and search for dsh-memento.
  3. Click Install; or install from the command line:
    bash
    dsh plugin --profile web add dsh-memento
    
  4. Restart DSH (or follow the restart prompt) so the plugin bundle takes effect.
  5. Back in Settings, confirm the memory plugin is enabled and note that memory data starts being written to local storage.
dsh-plugin-hub · Plugin Center
DSH Plugin Hub plugin market: search and install memory plugins like dsh-memento in one click

Notes

  1. Without a memory plugin, DSH cross-session memory is not reliable: memory-mode scope state lives only in the process and is lost on restart (source).
  2. GitHub-source memory plugins may lack build artifacts; if installation fails, switch to the npm version or wait for the beta release.
  3. Memory data lives locally (SQLite/files); uninstalling the plugin does not necessarily delete already-written memory files - clean those up separately.
  4. Memory persists conversation facts, so be mindful of where sensitive content is stored and what approval mechanism is in place.
  5. Running several memory plugins at once can overlap and double-inject context; start with one primary.
  6. If you cannot decide, sort the memory category in DSH Plugin Hub by stars and pick a verified one.

Sources: DeepSeek Harness source - welcome-store.ts, dsh-memento, graph-memory, dsh-meow-memory, dsh-auto-memory, dsh-memory

FAQ

What do DSH memory plugins do?

They let DeepSeek Harness remember information across sessions. DSH session state in memory-mode scopes lives only in the process and is lost on restart (confirmed in the official source), so without a memory plugin a new session knows nothing about the old one. Memory plugins persist important facts to local SQLite or files and auto-inject them into new sessions.

Which memory plugins can I choose for DeepSeek Harness?

The registry has many memory plugins. Representative picks: dsh-memory (project+global stores, Obsidian-style link graph), graph-memory (knowledge graph, 75% context compression), dsh-memento (approval-gated, auditable), dsh-auto-memory (three-layer auto memory, calendar reminders), and dsh-meow-memory (seven-layer SQLite, BM25 retrieval).

What is the difference between dsh-memory and graph-memory?

dsh-memory auto-extracts conversation facts into project and global stores organized as a link graph; graph-memory turns conversations into typed nodes and edges forming a knowledge graph, emphasizing semantic vector retrieval and context compression to recall relevant history instead of replaying full conversations.

Which memory plugin is best for beginners?

Check the install method first: npm-published plugins like dsh-memento, dsh-meow-memory and dsh-auto-memory install with one dsh plugin add <package> command; graph-memory is still beta and not on npm, so it needs a source build. For control and audit pick dsh-memento; for fully automatic pick dsh-auto-memory.

How do I install a memory plugin?

Open Settings -> Plugin Center in the Web UI (DSH Plugin Hub), search the plugin name and click Install; or run dsh plugin --profile web add <package> (npm) or dsh plugin --profile web add github:owner/repo (GitHub source). Restart for the bundle to load, then confirm the memory plugin is enabled and data is written locally.

Sources